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

Dataset: Open Web Text

Neuron 1857 in Layer 1

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: 4.9173. Min Range: -4.9173

Max Act: 4.9173. Min Act: -0.1700

Data Index: 7871526 (Open Web Text)

Max Activating Token Index: 644

Text #1

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.8566. Min Act: -0.1700

Data Index: 296480 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.8468. Min Act: -0.1700

Data Index: 1283910 (Open Web Text)

Max Activating Token Index: 621

Text #3

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7792. Min Act: -0.1700

Data Index: 2354325 (Open Web Text)

Max Activating Token Index: 623

Text #4

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7911. Min Act: -0.1700

Data Index: 2786793 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7669. Min Act: -0.1700

Data Index: 6795888 (Open Web Text)

Max Activating Token Index: 86

Text #6

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7572. Min Act: -0.1700

Data Index: 8525872 (Open Web Text)

Max Activating Token Index: 508

Text #7

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7643. Min Act: -0.1700

Data Index: 1818562 (Open Web Text)

Max Activating Token Index: 527

Text #8

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7256. Min Act: -0.1700

Data Index: 1113326 (Open Web Text)

Max Activating Token Index: 303

Text #9

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7159. Min Act: -0.1700

Data Index: 3973436 (Open Web Text)

Max Activating Token Index: 903

Text #10

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7447. Min Act: -0.1700

Data Index: 6830101 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7133. Min Act: -0.1700

Data Index: 6443214 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7016. Min Act: -0.1700

Data Index: 1234196 (Open Web Text)

Max Activating Token Index: 559

Text #13

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7033. Min Act: -0.1700

Data Index: 1909169 (Open Web Text)

Max Activating Token Index: 581

Text #14

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7104. Min Act: -0.1700

Data Index: 363249 (Open Web Text)

Max Activating Token Index: 523

Text #15

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.6825. Min Act: -0.1700

Data Index: 4048150 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7194. Min Act: -0.1700

Data Index: 4173438 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7111. Min Act: -0.1700

Data Index: 4464137 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.6921. Min Act: -0.1700

Data Index: 6099478 (Open Web Text)

Max Activating Token Index: 642

Text #19

Max Range: 4.9173. Min Range: -4.9173

Max Act: 4.7151. Min Act: -0.1700

Data Index: 1927037 (Open Web Text)

Max Activating Token Index: 488