Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3807 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.2229. Min Act: -0.0001

Data Index: 579645 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.2114. Min Act: -0.0001

Data Index: 728495 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1047176 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1770. Min Act: -0.0001

Data Index: 752262 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1861. Min Act: -0.0001

Data Index: 503531 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1936. Min Act: -0.0001

Data Index: 810338 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1823. Min Act: -0.0001

Data Index: 418102 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1863. Min Act: -0.0001

Data Index: 507288 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1931. Min Act: -0.0001

Data Index: 468952 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1979. Min Act: -0.0001

Data Index: 55374 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1915. Min Act: -0.0001

Data Index: 277417 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1359750 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1910. Min Act: -0.0001

Data Index: 435868 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1302188 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1037497 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1857. Min Act: -0.0001

Data Index: 645081 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1150343 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1850. Min Act: -0.0001

Data Index: 904427 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1727. Min Act: -0.0001

Data Index: 462487 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.2229. Min Range: -0.2229

Max Act: 0.1897. Min Act: -0.0001

Data Index: 390969 (C4 (Web Text))

Max Activating Token Index: 41