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

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

Neuron 905 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: 3.5898. Min Range: -3.5898

Max Act: 3.5898. Min Act: -0.1700

Data Index: 582484 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.5115. Min Act: -0.1700

Data Index: 56840 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4801. Min Act: -0.1700

Data Index: 522229 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.5271. Min Act: -0.1700

Data Index: 730667 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.5115. Min Act: -0.1700

Data Index: 1133900 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1181212 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4801. Min Act: -0.1700

Data Index: 90594 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4331. Min Act: -0.1700

Data Index: 240599 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4801. Min Act: -0.1700

Data Index: 540781 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3860. Min Act: -0.1700

Data Index: 875639 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1131716 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4488. Min Act: -0.1700

Data Index: 807420 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4331. Min Act: -0.1700

Data Index: 993125 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4331. Min Act: -0.1700

Data Index: 671038 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1000543 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3860. Min Act: -0.1700

Data Index: 1119301 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3860. Min Act: -0.1700

Data Index: 1103226 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3860. Min Act: -0.1700

Data Index: 1064974 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.4017. Min Act: -0.1700

Data Index: 1191990 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 3.5898. Min Range: -3.5898

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1019067 (C4 (Web Text))

Max Activating Token Index: 665