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

Dataset: Open Web Text

Neuron 857 in Layer 5

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: 4.1536. Min Range: -4.1536

Max Act: 4.1536. Min Act: -0.1700

Data Index: 603399 (Open Web Text)

Max Activating Token Index: 529

Text #1

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.1034. Min Act: -0.1700

Data Index: 8505803 (Open Web Text)

Max Activating Token Index: 782

Text #2

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0708. Min Act: -0.1700

Data Index: 415974 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0234. Min Act: -0.1700

Data Index: 1976281 (Open Web Text)

Max Activating Token Index: 653

Text #4

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0366. Min Act: -0.1700

Data Index: 8674629 (Open Web Text)

Max Activating Token Index: 268

Text #5

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0444. Min Act: -0.1700

Data Index: 6575131 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0112. Min Act: -0.1700

Data Index: 5720968 (Open Web Text)

Max Activating Token Index: 267

Text #7

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0335. Min Act: -0.1700

Data Index: 1423202 (Open Web Text)

Max Activating Token Index: 824

Text #8

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0106. Min Act: -0.1700

Data Index: 4132970 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0116. Min Act: -0.1700

Data Index: 5655741 (Open Web Text)

Max Activating Token Index: 863

Text #10

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0128. Min Act: -0.1700

Data Index: 7026761 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 4.1536. Min Range: -4.1536

Max Act: 3.9881. Min Act: -0.1700

Data Index: 1561067 (Open Web Text)

Max Activating Token Index: 975

Text #12

Max Range: 4.1536. Min Range: -4.1536

Max Act: 3.9857. Min Act: -0.1700

Data Index: 3422084 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 4.1536. Min Range: -4.1536

Max Act: 3.9798. Min Act: -0.1700

Data Index: 5804113 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 4.1536. Min Range: -4.1536

Max Act: 3.9851. Min Act: -0.1700

Data Index: 6017251 (Open Web Text)

Max Activating Token Index: 691

Text #15

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0096. Min Act: -0.1700

Data Index: 761839 (Open Web Text)

Max Activating Token Index: 565

Text #16

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0091. Min Act: -0.1700

Data Index: 6203124 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 4.1536. Min Range: -4.1536

Max Act: 3.9941. Min Act: -0.1700

Data Index: 6744735 (Open Web Text)

Max Activating Token Index: 939

Text #18

Max Range: 4.1536. Min Range: -4.1536

Max Act: 3.9819. Min Act: -0.1700

Data Index: 3952650 (Open Web Text)

Max Activating Token Index: 763

Text #19

Max Range: 4.1536. Min Range: -4.1536

Max Act: 4.0091. Min Act: -0.1700

Data Index: 3910394 (Open Web Text)

Max Activating Token Index: 394