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

Dataset: Open Web Text

Neuron 1629 in Layer 4

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: 4.5435. Min Range: -4.5435

Max Act: 4.5057. Min Act: -0.1700

Data Index: 1224754 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.4849. Min Act: -0.1700

Data Index: 1103129 (Open Web Text)

Max Activating Token Index: 634

Text #2

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.5435. Min Act: -0.1700

Data Index: 2364943 (Open Web Text)

Max Activating Token Index: 499

Text #3

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.4567. Min Act: -0.1700

Data Index: 7749546 (Open Web Text)

Max Activating Token Index: 993

Text #4

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.4643. Min Act: -0.1700

Data Index: 3305342 (Open Web Text)

Max Activating Token Index: 379

Text #5

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.4473. Min Act: -0.1700

Data Index: 315839 (Open Web Text)

Max Activating Token Index: 833

Text #6

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.3554. Min Act: -0.1700

Data Index: 915765 (Open Web Text)

Max Activating Token Index: 774

Text #7

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.3274. Min Act: -0.1700

Data Index: 3344886 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2988. Min Act: -0.1700

Data Index: 7298488 (Open Web Text)

Max Activating Token Index: 506

Text #9

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.3205. Min Act: -0.1700

Data Index: 6414337 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.3309. Min Act: -0.1700

Data Index: 5769378 (Open Web Text)

Max Activating Token Index: 989

Text #11

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2807. Min Act: -0.1700

Data Index: 1808139 (Open Web Text)

Max Activating Token Index: 617

Text #12

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2805. Min Act: -0.1700

Data Index: 285001 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.3079. Min Act: -0.1700

Data Index: 4142630 (Open Web Text)

Max Activating Token Index: 306

Text #14

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2682. Min Act: -0.1700

Data Index: 6780839 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2264. Min Act: -0.1700

Data Index: 2754388 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2287. Min Act: -0.1700

Data Index: 6647736 (Open Web Text)

Max Activating Token Index: 783

Text #17

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2195. Min Act: -0.1700

Data Index: 7469928 (Open Web Text)

Max Activating Token Index: 571

Text #18

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2467. Min Act: -0.1700

Data Index: 4303353 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 4.5435. Min Range: -4.5435

Max Act: 4.2367. Min Act: -0.1700

Data Index: 4464353 (Open Web Text)

Max Activating Token Index: 678