< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 3054 in Layer 6

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: 2.2964. Min Range: -2.2964

Max Act: 2.2952. Min Act: -0.1700

Data Index: 4036016 (Open Web Text)

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2697. Min Act: -0.1700

Data Index: 434434 (Open Web Text)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2815. Min Act: -0.1700

Data Index: 375224 (Open Web Text)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2964. Min Act: -0.1700

Data Index: 5428919 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2566. Min Act: -0.1700

Data Index: 1029597 (Open Web Text)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2550. Min Act: -0.1700

Data Index: 6128334 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2529. Min Act: -0.1700

Data Index: 3564269 (Open Web Text)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2316. Min Act: -0.1700

Data Index: 434436 (Open Web Text)

Max Activating Token Index: 295

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2265. Min Act: -0.1700

Data Index: 7952676 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2494. Min Act: -0.1700

Data Index: 4185560 (Open Web Text)

Max Activating Token Index: 613

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2309. Min Act: -0.1700

Data Index: 6172482 (Open Web Text)

Max Activating Token Index: 426

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2057. Min Act: -0.1700

Data Index: 1552221 (Open Web Text)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2252. Min Act: -0.1700

Data Index: 4142146 (Open Web Text)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2163. Min Act: -0.1700

Data Index: 434432 (Open Web Text)

Max Activating Token Index: 233

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2214. Min Act: -0.1700

Data Index: 434435 (Open Web Text)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.2089. Min Act: -0.1700

Data Index: 1392574 (Open Web Text)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.1849. Min Act: -0.1700

Data Index: 8481192 (Open Web Text)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.1869. Min Act: -0.1700

Data Index: 8165933 (Open Web Text)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.1785. Min Act: -0.1700

Data Index: 7751588 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2964. Min Range: -2.2964

Max Act: 2.1926. Min Act: -0.1700

Data Index: 3038223 (Open Web Text)

Max Activating Token Index: 875

Click toggle to see full text

Truncated

Full Text #19