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

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

Neuron 118 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: 3.7924. Min Range: -3.7924

Max Act: 3.7924. Min Act: -0.1700

Data Index: 755175 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6672. Min Act: -0.1700

Data Index: 219848 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6985. Min Act: -0.1700

Data Index: 454996 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6046. Min Act: -0.1700

Data Index: 195513 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.6359. Min Act: -0.1700

Data Index: 1253080 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5419. Min Act: -0.1700

Data Index: 1070387 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5733. Min Act: -0.1700

Data Index: 666720 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5419. Min Act: -0.1700

Data Index: 78388 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5106. Min Act: -0.1700

Data Index: 1308359 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5106. Min Act: -0.1700

Data Index: 542604 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.5106. Min Act: -0.1700

Data Index: 669626 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4793. Min Act: -0.1700

Data Index: 1152878 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4793. Min Act: -0.1700

Data Index: 604640 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4479. Min Act: -0.1700

Data Index: 235056 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4009. Min Act: -0.1700

Data Index: 1300715 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.3852. Min Act: -0.1700

Data Index: 608747 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4166. Min Act: -0.1700

Data Index: 141324 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4166. Min Act: -0.1700

Data Index: 132097 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4009. Min Act: -0.1700

Data Index: 1134872 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.7924. Min Range: -3.7924

Max Act: 3.4166. Min Act: -0.1700

Data Index: 663857 (C4 (Web Text))

Max Activating Token Index: 150