Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5580 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5717. Min Range: -2.5717

Max Act: 2.5717. Min Act: -0.0000

Data Index: 738597 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 2.5717. Min Range: -2.5717

Max Act: 2.4376. Min Act: -0.0000

Data Index: 319418 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.5717. Min Range: -2.5717

Max Act: 2.4052. Min Act: -0.0000

Data Index: 875274 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 2.5717. Min Range: -2.5717

Max Act: 2.0684. Min Act: -0.0000

Data Index: 166262 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 2.5717. Min Range: -2.5717

Max Act: 2.1410. Min Act: -0.0000

Data Index: 1355861 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.9241. Min Act: -0.0000

Data Index: 9256 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 2.5717. Min Range: -2.5717

Max Act: 2.0211. Min Act: -0.0000

Data Index: 701280 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.9675. Min Act: -0.0000

Data Index: 907275 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.7166. Min Act: -0.0000

Data Index: 764526 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.8035. Min Act: -0.0000

Data Index: 1229797 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.8723. Min Act: -0.0000

Data Index: 1070925 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.7135. Min Act: -0.0000

Data Index: 128727 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.8042. Min Act: -0.0000

Data Index: 964540 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.8980. Min Act: -0.0000

Data Index: 847903 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.6534. Min Act: -0.0000

Data Index: 382205 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.7291. Min Act: -0.0000

Data Index: 55277 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.7447. Min Act: -0.0000

Data Index: 69169 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1055197 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.7304. Min Act: -0.0000

Data Index: 14665 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 2.5717. Min Range: -2.5717

Max Act: 1.6253. Min Act: -0.0000

Data Index: 328967 (C4 (Web Text))

Max Activating Token Index: 1010