Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 267 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 12.0428. Min Range: -12.0428

Max Act: 12.0428. Min Act: -0.1700

Data Index: 260478 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.7928. Min Act: -0.1699

Data Index: 626621 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.6678. Min Act: -0.1700

Data Index: 524012 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.6053. Min Act: -0.1700

Data Index: 1057855 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.4178. Min Act: -0.1700

Data Index: 273860 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.5428. Min Act: -0.1700

Data Index: 1063788 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.4178. Min Act: -0.1700

Data Index: 761460 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.4803. Min Act: -0.1700

Data Index: 184178 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.3553. Min Act: -0.1700

Data Index: 653081 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.3553. Min Act: -0.1700

Data Index: 811744 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.2928. Min Act: -0.1700

Data Index: 962238 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.2303. Min Act: -0.1700

Data Index: 405736 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.2928. Min Act: -0.1700

Data Index: 466429 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.2928. Min Act: -0.1700

Data Index: 929795 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.1678. Min Act: -0.1700

Data Index: 877993 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.1678. Min Act: -0.1699

Data Index: 989966 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.1678. Min Act: -0.1700

Data Index: 682283 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.1053. Min Act: -0.1700

Data Index: 1226311 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.1678. Min Act: -0.1700

Data Index: 12825 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 12.0428. Min Range: -12.0428

Max Act: 11.0428. Min Act: -0.1700

Data Index: 322201 (C4 (Web Text))

Max Activating Token Index: 480