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

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

Neuron 5997 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0282. Min Range: -1.0282

Max Act: 1.0282. Min Act: -0.0000

Data Index: 150364 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.9007. Min Act: -0.0000

Data Index: 885425 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1005013 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.8301. Min Act: -0.0000

Data Index: 234119 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.7873. Min Act: -0.0000

Data Index: 656083 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.7785. Min Act: -0.0000

Data Index: 677813 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.7222. Min Act: -0.0000

Data Index: 72910 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.7582. Min Act: -0.0000

Data Index: 423154 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.7513. Min Act: -0.0000

Data Index: 450813 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6981. Min Act: 0.0000

Data Index: 177272 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6764. Min Act: -0.0000

Data Index: 849445 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.7223. Min Act: -0.0000

Data Index: 652165 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6510. Min Act: -0.0000

Data Index: 844581 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6943. Min Act: -0.0000

Data Index: 510201 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6950. Min Act: -0.0000

Data Index: 732633 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6770. Min Act: -0.0000

Data Index: 740116 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6304. Min Act: -0.0000

Data Index: 560533 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1290209 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6277. Min Act: -0.0000

Data Index: 852086 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 1.0282. Min Range: -1.0282

Max Act: 0.6687. Min Act: -0.0000

Data Index: 421813 (C4 (Web Text))

Max Activating Token Index: 628