Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 452 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.1930. Min Range: -7.1930

Max Act: 7.1930. Min Act: -0.1700

Data Index: 1292717 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 7.1930. Min Range: -7.1930

Max Act: 7.0992. Min Act: -0.1700

Data Index: 561095 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.7867. Min Act: -0.1700

Data Index: 1008359 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.7555. Min Act: -0.1700

Data Index: 1228071 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.7867. Min Act: -0.1700

Data Index: 84285 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.7242. Min Act: -0.1700

Data Index: 389456 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5992. Min Act: -0.1700

Data Index: 1348138 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5992. Min Act: -0.1698

Data Index: 54783 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.6305. Min Act: -0.1700

Data Index: 162223 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5992. Min Act: -0.1700

Data Index: 746929 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5367. Min Act: -0.1700

Data Index: 515314 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5992. Min Act: -0.1515

Data Index: 1192459 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5680. Min Act: -0.1700

Data Index: 1069986 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.6305. Min Act: -0.1700

Data Index: 1233541 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.4742. Min Act: -0.1700

Data Index: 147086 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5680. Min Act: -0.1700

Data Index: 320839 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.4742. Min Act: -0.1700

Data Index: 793989 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.6305. Min Act: -0.1700

Data Index: 1027001 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.4742. Min Act: -0.1700

Data Index: 943229 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 7.1930. Min Range: -7.1930

Max Act: 6.5367. Min Act: -0.1698

Data Index: 933145 (C4 (Web Text))

Max Activating Token Index: 111