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

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

Neuron 2361 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7941. Min Act: -0.0001

Data Index: 31781 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.7178. Min Act: -0.0001

Data Index: 635087 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5971. Min Act: -0.0001

Data Index: 677945 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.6120. Min Act: -0.0000

Data Index: 357396 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5946. Min Act: -0.0000

Data Index: 95866 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5615. Min Act: -0.0000

Data Index: 766250 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5273. Min Act: -0.0001

Data Index: 1320663 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5339. Min Act: -0.0001

Data Index: 268793 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5465. Min Act: -0.0000

Data Index: 203544 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1241805 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5210. Min Act: -0.0001

Data Index: 1107979 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5213. Min Act: -0.0001

Data Index: 426911 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5035. Min Act: -0.0001

Data Index: 190028 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.5059. Min Act: -0.0001

Data Index: 1194512 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.4961. Min Act: -0.0001

Data Index: 1063048 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.4951. Min Act: -0.0001

Data Index: 1132637 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.4824. Min Act: -0.0001

Data Index: 320646 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.4535. Min Act: -0.0000

Data Index: 912257 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.4630. Min Act: -0.0001

Data Index: 366531 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.7941. Min Range: -0.7941

Max Act: 0.4455. Min Act: -0.0001

Data Index: 72437 (C4 (Web Text))

Max Activating Token Index: 438