Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1493 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.9391. Min Act: -0.1700

Data Index: 325698 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.9391. Min Act: -0.1700

Data Index: 974167 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.9078. Min Act: -0.1700

Data Index: 221702 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.9078. Min Act: -0.1700

Data Index: 235357 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.8453. Min Act: -0.1700

Data Index: 420808 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.8453. Min Act: -0.1700

Data Index: 832934 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.7827. Min Act: -0.1700

Data Index: 275508 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.7514. Min Act: -0.1700

Data Index: 610341 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.7514. Min Act: -0.1700

Data Index: 1232036 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6888. Min Act: -0.1700

Data Index: 998708 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6888. Min Act: -0.1700

Data Index: 164569 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6575. Min Act: -0.1700

Data Index: 1108424 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6888. Min Act: -0.1699

Data Index: 959336 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6888. Min Act: -0.1700

Data Index: 1105034 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6575. Min Act: -0.1700

Data Index: 191136 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6575. Min Act: -0.1700

Data Index: 302109 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.7514. Min Act: -0.1700

Data Index: 1067660 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6575. Min Act: -0.1700

Data Index: 948594 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6575. Min Act: -0.1700

Data Index: 688202 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.6575. Min Act: -0.1700

Data Index: 553136 (C4 (Web Text))

Max Activating Token Index: 779