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

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

Neuron 1705 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: 5.0183. Min Range: -5.0183

Max Act: 4.9871. Min Act: -0.1700

Data Index: 1352952 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 5.0183. Min Range: -5.0183

Max Act: 5.0183. Min Act: -0.1700

Data Index: 282061 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 5.0183. Min Range: -5.0183

Max Act: 5.0183. Min Act: -0.1700

Data Index: 761210 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.8933. Min Act: -0.1700

Data Index: 102468 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7683. Min Act: -0.1700

Data Index: 888231 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7996. Min Act: -0.1700

Data Index: 1270164 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7683. Min Act: -0.1700

Data Index: 1147592 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7058. Min Act: -0.1700

Data Index: 533965 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7058. Min Act: -0.1700

Data Index: 1335889 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7683. Min Act: -0.1700

Data Index: 617437 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7371. Min Act: -0.1700

Data Index: 1200643 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.6746. Min Act: -0.1700

Data Index: 117351 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7371. Min Act: -0.1700

Data Index: 336111 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.6746. Min Act: -0.1700

Data Index: 683444 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7371. Min Act: -0.1700

Data Index: 411545 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7058. Min Act: -0.1700

Data Index: 629561 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7058. Min Act: -0.1700

Data Index: 647010 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7058. Min Act: -0.1700

Data Index: 914903 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.6746. Min Act: -0.1699

Data Index: 1027365 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 5.0183. Min Range: -5.0183

Max Act: 4.7683. Min Act: -0.1700

Data Index: 466254 (C4 (Web Text))

Max Activating Token Index: 171