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

Dataset: Open Web Text

Neuron 1794 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: 3.2939. Min Range: -3.2939

Max Act: 3.2939. Min Act: -0.1700

Data Index: 5337563 (Open Web Text)

Max Activating Token Index: 556

Text #1

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2867. Min Act: -0.1700

Data Index: 3960815 (Open Web Text)

Max Activating Token Index: 762

Text #2

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2623. Min Act: -0.1700

Data Index: 7090466 (Open Web Text)

Max Activating Token Index: 558

Text #3

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2635. Min Act: -0.1700

Data Index: 4032802 (Open Web Text)

Max Activating Token Index: 924

Text #4

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2467. Min Act: -0.1700

Data Index: 3378080 (Open Web Text)

Max Activating Token Index: 411

Text #5

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2426. Min Act: -0.1700

Data Index: 1781902 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2502. Min Act: -0.1700

Data Index: 8417154 (Open Web Text)

Max Activating Token Index: 526

Text #7

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2480. Min Act: -0.1700

Data Index: 8359743 (Open Web Text)

Max Activating Token Index: 145

Text #8

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2356. Min Act: -0.1700

Data Index: 643125 (Open Web Text)

Max Activating Token Index: 202

Text #9

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2282. Min Act: -0.1700

Data Index: 1274683 (Open Web Text)

Max Activating Token Index: 545

Text #10

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2388. Min Act: -0.1700

Data Index: 2466270 (Open Web Text)

Max Activating Token Index: 703

Text #11

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2260. Min Act: -0.1700

Data Index: 1942040 (Open Web Text)

Max Activating Token Index: 250

Text #12

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2273. Min Act: -0.1700

Data Index: 5935957 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2025. Min Act: -0.1700

Data Index: 7173252 (Open Web Text)

Max Activating Token Index: 311

Text #14

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1979. Min Act: -0.1700

Data Index: 3364233 (Open Web Text)

Max Activating Token Index: 388

Text #15

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2071. Min Act: -0.1700

Data Index: 1186052 (Open Web Text)

Max Activating Token Index: 230

Text #16

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2078. Min Act: -0.1700

Data Index: 8553052 (Open Web Text)

Max Activating Token Index: 991

Text #17

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.2209. Min Act: -0.1700

Data Index: 4479596 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1890. Min Act: -0.1700

Data Index: 2318040 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 3.2939. Min Range: -3.2939

Max Act: 3.1833. Min Act: -0.1700

Data Index: 4120111 (Open Web Text)

Max Activating Token Index: 354