Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3840 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2917. Min Act: -0.0000

Data Index: 67020 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2581. Min Act: -0.0000

Data Index: 3956 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2258. Min Act: -0.0000

Data Index: 728775 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2585. Min Act: -0.0000

Data Index: 155865 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2374. Min Act: -0.0000

Data Index: 861464 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1049793 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2343. Min Act: -0.0000

Data Index: 867436 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2312. Min Act: -0.0001

Data Index: 3605 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2176. Min Act: -0.0000

Data Index: 387561 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2276. Min Act: -0.0000

Data Index: 224185 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1312589 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1174513 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1005360 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2102. Min Act: -0.0001

Data Index: 466865 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2175. Min Act: -0.0000

Data Index: 666877 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1860. Min Act: -0.0000

Data Index: 667564 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1950. Min Act: -0.0000

Data Index: 727371 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1946. Min Act: -0.0000

Data Index: 451588 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1642. Min Act: -0.0000

Data Index: 668050 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.1852. Min Act: -0.0000

Data Index: 493810 (C4 (Web Text))

Max Activating Token Index: 797