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

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

Neuron 3130 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: 0.4448. Min Range: -0.4448

Max Act: 0.4448. Min Act: -0.0001

Data Index: 1181705 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1087422 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3626. Min Act: -0.0000

Data Index: 948827 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1253317 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1215481 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3666. Min Act: -0.0000

Data Index: 851653 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3528. Min Act: -0.0000

Data Index: 437949 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3321. Min Act: -0.0001

Data Index: 158563 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3378. Min Act: -0.0000

Data Index: 111821 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3774. Min Act: -0.0000

Data Index: 518415 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3238. Min Act: -0.0000

Data Index: 507242 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3377. Min Act: -0.0000

Data Index: 789270 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3353. Min Act: -0.0000

Data Index: 423154 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3448. Min Act: -0.0001

Data Index: 1097570 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1025866 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3208. Min Act: -0.0000

Data Index: 587380 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1354795 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.2973. Min Act: -0.0000

Data Index: 120517 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3045. Min Act: -0.0000

Data Index: 857976 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.4448. Min Range: -0.4448

Max Act: 0.3151. Min Act: -0.0000

Data Index: 420718 (C4 (Web Text))

Max Activating Token Index: 910