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

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

Neuron 1535 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: 7.2227. Min Range: -7.2227

Max Act: 7.2227. Min Act: -0.1700

Data Index: 1079863 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 7.2227. Min Range: -7.2227

Max Act: 7.1915. Min Act: -0.1700

Data Index: 1217891 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 7.2227. Min Range: -7.2227

Max Act: 7.1602. Min Act: -0.1700

Data Index: 406140 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 7.2227. Min Range: -7.2227

Max Act: 7.0977. Min Act: -0.1700

Data Index: 441162 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.9102. Min Act: -0.1700

Data Index: 85148 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.9727. Min Act: -0.1700

Data Index: 396250 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.9727. Min Act: -0.1700

Data Index: 301933 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.9102. Min Act: -0.1700

Data Index: 915397 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.8165. Min Act: -0.1700

Data Index: 307852 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.8165. Min Act: -0.1700

Data Index: 1203908 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.7852. Min Act: -0.1699

Data Index: 844242 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.8165. Min Act: -0.1700

Data Index: 614923 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.7852. Min Act: -0.1700

Data Index: 527651 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.8165. Min Act: -0.1700

Data Index: 59473 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.7852. Min Act: -0.1700

Data Index: 510130 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.7852. Min Act: -0.1700

Data Index: 827696 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.7540. Min Act: -0.1700

Data Index: 1152065 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.6915. Min Act: -0.1700

Data Index: 81444 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.7227. Min Act: -0.1700

Data Index: 789733 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 7.2227. Min Range: -7.2227

Max Act: 6.6602. Min Act: -0.1700

Data Index: 14721 (C4 (Web Text))

Max Activating Token Index: 14