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

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

Neuron 656 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: 5.2109. Min Range: -5.2109

Max Act: 5.2109. Min Act: -0.1700

Data Index: 205381 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 5.2109. Min Range: -5.2109

Max Act: 5.0859. Min Act: -0.1700

Data Index: 827733 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 5.2109. Min Range: -5.2109

Max Act: 5.0859. Min Act: -0.1700

Data Index: 16593 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 5.2109. Min Range: -5.2109

Max Act: 5.0547. Min Act: -0.1700

Data Index: 261310 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 5.2109. Min Range: -5.2109

Max Act: 5.0234. Min Act: -0.1700

Data Index: 273362 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 5.2109. Min Range: -5.2109

Max Act: 5.0234. Min Act: -0.1700

Data Index: 1177274 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 5.2109. Min Range: -5.2109

Max Act: 5.0234. Min Act: -0.1700

Data Index: 185036 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.9297. Min Act: -0.1700

Data Index: 292532 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 5.2109. Min Range: -5.2109

Max Act: 5.0547. Min Act: -0.1700

Data Index: 977989 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8984. Min Act: -0.1700

Data Index: 702809 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8984. Min Act: -0.1700

Data Index: 730743 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8984. Min Act: -0.1700

Data Index: 1341150 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8984. Min Act: -0.1700

Data Index: 1008729 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8672. Min Act: -0.1700

Data Index: 362683 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8984. Min Act: -0.1700

Data Index: 497928 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8047. Min Act: -0.1700

Data Index: 757272 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8359. Min Act: -0.1700

Data Index: 426700 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8047. Min Act: -0.1700

Data Index: 1164603 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8359. Min Act: -0.1700

Data Index: 639254 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 5.2109. Min Range: -5.2109

Max Act: 4.8359. Min Act: -0.1700

Data Index: 251287 (C4 (Web Text))

Max Activating Token Index: 835