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

Dataset: Open Web Text

Neuron 1761 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: 3.4949. Min Range: -3.4949

Max Act: 3.4949. Min Act: -0.1700

Data Index: 3936040 (Open Web Text)

Max Activating Token Index: 749

Text #1

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.4330. Min Act: -0.1700

Data Index: 2627362 (Open Web Text)

Max Activating Token Index: 131

Text #2

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3826. Min Act: -0.1700

Data Index: 22369 (Open Web Text)

Max Activating Token Index: 844

Text #3

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3908. Min Act: -0.1700

Data Index: 1017387 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3312. Min Act: -0.1700

Data Index: 5573142 (Open Web Text)

Max Activating Token Index: 707

Text #5

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1201822 (Open Web Text)

Max Activating Token Index: 143

Text #6

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3610. Min Act: -0.1700

Data Index: 3219547 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3112. Min Act: -0.1700

Data Index: 714519 (Open Web Text)

Max Activating Token Index: 38

Text #8

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3066. Min Act: -0.1700

Data Index: 1475866 (Open Web Text)

Max Activating Token Index: 283

Text #9

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.3132. Min Act: -0.1700

Data Index: 8272034 (Open Web Text)

Max Activating Token Index: 484

Text #10

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.1365. Min Act: -0.1700

Data Index: 6378730 (Open Web Text)

Max Activating Token Index: 577

Text #11

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2987. Min Act: -0.1700

Data Index: 1240790 (Open Web Text)

Max Activating Token Index: 73

Text #12

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2422. Min Act: -0.1700

Data Index: 6361395 (Open Web Text)

Max Activating Token Index: 873

Text #13

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2573. Min Act: -0.1700

Data Index: 6666408 (Open Web Text)

Max Activating Token Index: 379

Text #14

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2044. Min Act: -0.1700

Data Index: 7177173 (Open Web Text)

Max Activating Token Index: 178

Text #15

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2204. Min Act: -0.1700

Data Index: 327775 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2418. Min Act: -0.1700

Data Index: 1621550 (Open Web Text)

Max Activating Token Index: 824

Text #17

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2422. Min Act: -0.1700

Data Index: 7913083 (Open Web Text)

Max Activating Token Index: 232

Text #18

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2176. Min Act: -0.1700

Data Index: 1147703 (Open Web Text)

Max Activating Token Index: 25

Text #19

Max Range: 3.4949. Min Range: -3.4949

Max Act: 3.2379. Min Act: -0.1700

Data Index: 579607 (Open Web Text)

Max Activating Token Index: 910