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

Dataset: Open Web Text

Neuron 1695 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: 3.6803. Min Range: -3.6803

Max Act: 3.6803. Min Act: -0.1700

Data Index: 948260 (Open Web Text)

Max Activating Token Index: 805

Text #1

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.5532. Min Act: -0.1700

Data Index: 4653552 (Open Web Text)

Max Activating Token Index: 777

Text #2

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.4746. Min Act: -0.1700

Data Index: 2127145 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.4415. Min Act: -0.1700

Data Index: 7321436 (Open Web Text)

Max Activating Token Index: 680

Text #4

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.3732. Min Act: -0.1700

Data Index: 7733172 (Open Web Text)

Max Activating Token Index: 70

Text #5

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.3569. Min Act: -0.1700

Data Index: 6055942 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.3327. Min Act: -0.1700

Data Index: 1832862 (Open Web Text)

Max Activating Token Index: 348

Text #7

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.3068. Min Act: -0.1700

Data Index: 3673620 (Open Web Text)

Max Activating Token Index: 234

Text #8

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.2828. Min Act: -0.1700

Data Index: 6899563 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.2761. Min Act: -0.1700

Data Index: 5377970 (Open Web Text)

Max Activating Token Index: 627

Text #10

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.2273. Min Act: -0.1700

Data Index: 177755 (Open Web Text)

Max Activating Token Index: 383

Text #11

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.2156. Min Act: -0.1700

Data Index: 8484506 (Open Web Text)

Max Activating Token Index: 265

Text #12

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.2114. Min Act: -0.1700

Data Index: 6735365 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.2209. Min Act: -0.1700

Data Index: 6881332 (Open Web Text)

Max Activating Token Index: 653

Text #14

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.1978. Min Act: -0.1700

Data Index: 3422506 (Open Web Text)

Max Activating Token Index: 299

Text #15

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.2141. Min Act: -0.1700

Data Index: 5087328 (Open Web Text)

Max Activating Token Index: 554

Text #16

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.1899. Min Act: -0.1700

Data Index: 7240762 (Open Web Text)

Max Activating Token Index: 127

Text #17

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.1829. Min Act: -0.1700

Data Index: 7964603 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.1627. Min Act: -0.1700

Data Index: 6511348 (Open Web Text)

Max Activating Token Index: 568

Text #19

Max Range: 3.6803. Min Range: -3.6803

Max Act: 3.1672. Min Act: -0.1700

Data Index: 1706781 (Open Web Text)

Max Activating Token Index: 555