< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 843 in Layer 2

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: 2.3132. Min Range: -2.3132

Max Act: 2.3132. Min Act: -0.1700

Data Index: 72754 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.2374. Min Act: -0.1700

Data Index: 8650292 (Open Web Text)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.2320. Min Act: -0.1700

Data Index: 6294608 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.2221. Min Act: -0.1700

Data Index: 2478918 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.2098. Min Act: -0.1700

Data Index: 8343411 (Open Web Text)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.2172. Min Act: -0.1700

Data Index: 2846156 (Open Web Text)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.2301. Min Act: -0.1700

Data Index: 4180274 (Open Web Text)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1877. Min Act: -0.1700

Data Index: 440504 (Open Web Text)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1876. Min Act: -0.1700

Data Index: 3735026 (Open Web Text)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1689. Min Act: -0.1700

Data Index: 20278 (Open Web Text)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1573. Min Act: -0.1700

Data Index: 4313494 (Open Web Text)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1514. Min Act: -0.1700

Data Index: 6636786 (Open Web Text)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1545. Min Act: -0.1700

Data Index: 2251405 (Open Web Text)

Max Activating Token Index: 315

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1433. Min Act: -0.1700

Data Index: 5204632 (Open Web Text)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1511. Min Act: -0.1700

Data Index: 3064560 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1607. Min Act: -0.1700

Data Index: 6439688 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1450. Min Act: -0.1700

Data Index: 5307173 (Open Web Text)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1509. Min Act: -0.1700

Data Index: 2701577 (Open Web Text)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1607. Min Act: -0.1700

Data Index: 5703480 (Open Web Text)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3132. Min Range: -2.3132

Max Act: 2.1761. Min Act: -0.1700

Data Index: 3630146 (Open Web Text)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #19