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

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

Neuron 3685 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6221. Min Range: -5.6221

Max Act: 5.6221. Min Act: -0.0000

Data Index: 456729 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.9523. Min Act: -0.0000

Data Index: 1150317 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.9633. Min Act: -0.0000

Data Index: 1131384 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.5438. Min Act: -0.0000

Data Index: 226453 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.4063. Min Act: -0.0000

Data Index: 551137 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.4410. Min Act: -0.0000

Data Index: 581013 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.8316. Min Act: -0.0000

Data Index: 1189422 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.6048. Min Act: -0.0001

Data Index: 437707 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.9360. Min Act: -0.0000

Data Index: 725850 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.6109. Min Act: -0.0001

Data Index: 677411 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.7285. Min Act: -0.0000

Data Index: 389180 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.2689. Min Act: -0.0000

Data Index: 39091 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.7866. Min Act: -0.0000

Data Index: 1296060 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.1754. Min Act: -0.0000

Data Index: 992902 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.1399. Min Act: -0.0000

Data Index: 46523 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.1125. Min Act: -0.0000

Data Index: 864594 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.2628. Min Act: -0.0000

Data Index: 864625 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.3673. Min Act: -0.0000

Data Index: 1344200 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.2165. Min Act: -0.0000

Data Index: 55317 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 5.6221. Min Range: -5.6221

Max Act: 4.2082. Min Act: -0.0000

Data Index: 305617 (C4 (Web Text))

Max Activating Token Index: 917