Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 100 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.7464. Min Act: 0.0000

Data Index: 1019702 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.6379. Min Act: -0.0000

Data Index: 344090 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1189420 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5941. Min Act: -0.0000

Data Index: 754348 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5832. Min Act: -0.0000

Data Index: 327749 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5833. Min Act: -0.0000

Data Index: 206000 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5628. Min Act: -0.0000

Data Index: 619307 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5630. Min Act: -0.0000

Data Index: 991922 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5459. Min Act: 0.0000

Data Index: 622420 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1276683 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5166. Min Act: -0.0000

Data Index: 263798 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5275. Min Act: -0.0000

Data Index: 978709 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4897. Min Act: -0.0000

Data Index: 928285 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5362. Min Act: -0.0000

Data Index: 301304 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1240002 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5197. Min Act: 0.0000

Data Index: 1345391 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1092081 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4869. Min Act: 0.0000

Data Index: 166579 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.5146. Min Act: -0.0000

Data Index: 211302 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.7464. Min Range: -0.7464

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1033669 (C4 (Web Text))

Max Activating Token Index: 964