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

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

Neuron 1242 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: 0.3688. Min Range: -0.3688

Max Act: 0.3688. Min Act: -0.0000

Data Index: 115741 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3428. Min Act: -0.0000

Data Index: 830434 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3451. Min Act: -0.0000

Data Index: 153698 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3518. Min Act: -0.0000

Data Index: 236891 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3483. Min Act: -0.0001

Data Index: 217583 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3259. Min Act: -0.0000

Data Index: 295924 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3237. Min Act: -0.0000

Data Index: 289238 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3207. Min Act: -0.0000

Data Index: 272405 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3266. Min Act: -0.0000

Data Index: 771024 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3149. Min Act: -0.0001

Data Index: 843390 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3057. Min Act: -0.0000

Data Index: 134339 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2919. Min Act: 0.0000

Data Index: 1043970 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3112. Min Act: -0.0001

Data Index: 86585 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3121. Min Act: -0.0000

Data Index: 56117 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2879. Min Act: -0.0001

Data Index: 611230 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2881. Min Act: -0.0000

Data Index: 944614 (C4 (Web Text))

Max Activating Token Index: 107

Text #16

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3089. Min Act: -0.0000

Data Index: 592441 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2948. Min Act: -0.0000

Data Index: 71181 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2941. Min Act: -0.0000

Data Index: 596399 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2918. Min Act: -0.0000

Data Index: 518989 (C4 (Web Text))

Max Activating Token Index: 660