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

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

Neuron 3139 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.8816. Min Act: -0.0000

Data Index: 1198585 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.7667. Min Act: -0.0000

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.8844. Min Act: -0.0000

Data Index: 150368 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.7544. Min Act: -0.0000

Data Index: 345555 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.7330. Min Act: -0.0000

Data Index: 418410 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.7137. Min Act: -0.0000

Data Index: 321369 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6878. Min Act: -0.0000

Data Index: 661575 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.7296. Min Act: -0.0000

Data Index: 532734 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1176104 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.7226. Min Act: -0.0000

Data Index: 45678 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6508. Min Act: -0.0000

Data Index: 49039 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6516. Min Act: 0.0002

Data Index: 702959 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6124. Min Act: -0.0000

Data Index: 772073 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6300. Min Act: -0.0000

Data Index: 994592 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.7076. Min Act: -0.0000

Data Index: 662915 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6397. Min Act: -0.0000

Data Index: 631571 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1058063 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.5074. Min Act: -0.0000

Data Index: 381343 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.6388. Min Act: -0.0000

Data Index: 632058 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.8844. Min Range: -0.8844

Max Act: 0.5543. Min Act: -0.0000

Data Index: 121420 (C4 (Web Text))

Max Activating Token Index: 856