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

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

Neuron 877 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.9211. Min Act: -0.1689

Data Index: 1130432 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.7961. Min Act: -0.1700

Data Index: 733206 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.7024. Min Act: -0.1700

Data Index: 980853 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.7336. Min Act: -0.1700

Data Index: 620398 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6711. Min Act: -0.1700

Data Index: 14433 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6711. Min Act: -0.1700

Data Index: 932321 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6399. Min Act: -0.1700

Data Index: 927195 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6399. Min Act: -0.1700

Data Index: 1197291 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6399. Min Act: -0.1700

Data Index: 1223795 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6711. Min Act: -0.1700

Data Index: 1169767 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6399. Min Act: -0.1700

Data Index: 1200365 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6086. Min Act: -0.1700

Data Index: 1049645 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6086. Min Act: -0.1700

Data Index: 1229875 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6086. Min Act: -0.1700

Data Index: 469307 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.5774. Min Act: -0.1700

Data Index: 151094 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.5461. Min Act: -0.1700

Data Index: 707220 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.5774. Min Act: -0.1700

Data Index: 1086833 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6086. Min Act: -0.1700

Data Index: 406181 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.6086. Min Act: -0.1700

Data Index: 257153 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 5.9211. Min Range: -5.9211

Max Act: 5.5774. Min Act: -0.1700

Data Index: 1269827 (C4 (Web Text))

Max Activating Token Index: 879