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

Dataset: Open Web Text

Neuron 2907 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: 3.5159. Min Range: -3.5159

Max Act: 3.5159. Min Act: -0.1700

Data Index: 2744704 (Open Web Text)

Max Activating Token Index: 601

Text #1

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.4955. Min Act: -0.1700

Data Index: 1517891 (Open Web Text)

Max Activating Token Index: 827

Text #2

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.5010. Min Act: -0.1700

Data Index: 5975308 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.4659. Min Act: -0.1700

Data Index: 6796192 (Open Web Text)

Max Activating Token Index: 147

Text #4

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.4528. Min Act: -0.1700

Data Index: 1678158 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.4142. Min Act: -0.1700

Data Index: 3638763 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3990. Min Act: -0.1700

Data Index: 3862968 (Open Web Text)

Max Activating Token Index: 207

Text #7

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.4001. Min Act: -0.1700

Data Index: 4209479 (Open Web Text)

Max Activating Token Index: 561

Text #8

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3750. Min Act: -0.1700

Data Index: 5022498 (Open Web Text)

Max Activating Token Index: 843

Text #9

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3690. Min Act: -0.1700

Data Index: 6833533 (Open Web Text)

Max Activating Token Index: 888

Text #10

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3508. Min Act: -0.1700

Data Index: 2451313 (Open Web Text)

Max Activating Token Index: 583

Text #11

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3546. Min Act: -0.1700

Data Index: 5089471 (Open Web Text)

Max Activating Token Index: 658

Text #12

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3501. Min Act: -0.1700

Data Index: 7138192 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3419. Min Act: -0.1700

Data Index: 2527157 (Open Web Text)

Max Activating Token Index: 957

Text #14

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3410. Min Act: -0.1700

Data Index: 7532697 (Open Web Text)

Max Activating Token Index: 735

Text #15

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3385. Min Act: -0.1700

Data Index: 2197006 (Open Web Text)

Max Activating Token Index: 676

Text #16

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3279. Min Act: -0.1700

Data Index: 5276440 (Open Web Text)

Max Activating Token Index: 762

Text #17

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3269. Min Act: -0.1700

Data Index: 1565593 (Open Web Text)

Max Activating Token Index: 82

Text #18

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3173. Min Act: -0.1700

Data Index: 1231659 (Open Web Text)

Max Activating Token Index: 366

Text #19

Max Range: 3.5159. Min Range: -3.5159

Max Act: 3.3210. Min Act: -0.1700

Data Index: 2622563 (Open Web Text)

Max Activating Token Index: 579