< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 473 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.3675. Min Act: -0.1700

Data Index: 6749025 (Open Web Text)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.3429. Min Act: -0.1700

Data Index: 5161231 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.3368. Min Act: -0.1700

Data Index: 1487578 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.3388. Min Act: -0.1700

Data Index: 1891550 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.2424. Min Act: -0.1700

Data Index: 1390858 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.2542. Min Act: -0.1700

Data Index: 4630515 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1958. Min Act: -0.1700

Data Index: 3420273 (Open Web Text)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1849. Min Act: -0.1700

Data Index: 8309224 (Open Web Text)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.2227. Min Act: -0.1700

Data Index: 6340846 (Open Web Text)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1572. Min Act: -0.1700

Data Index: 7448937 (Open Web Text)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1362. Min Act: -0.1700

Data Index: 4520659 (Open Web Text)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1741. Min Act: -0.1700

Data Index: 2785446 (Open Web Text)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1547. Min Act: -0.1700

Data Index: 3619539 (Open Web Text)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1327. Min Act: -0.1700

Data Index: 4629278 (Open Web Text)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1429. Min Act: -0.1700

Data Index: 2700006 (Open Web Text)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1076. Min Act: -0.1700

Data Index: 7812813 (Open Web Text)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1514. Min Act: -0.1700

Data Index: 1841017 (Open Web Text)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.0940. Min Act: -0.1700

Data Index: 1800920 (Open Web Text)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.1397. Min Act: -0.1700

Data Index: 1804717 (Open Web Text)

Max Activating Token Index: 565

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.3675. Min Range: -4.3675

Max Act: 4.0898. Min Act: -0.1700

Data Index: 3021154 (Open Web Text)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #19