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

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

Neuron 3997 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0014. Min Range: -6.0014

Max Act: 5.7393. Min Act: -0.0000

Data Index: 346551 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 6.0014. Min Range: -6.0014

Max Act: 6.0014. Min Act: -0.0000

Data Index: 522515 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 6.0014. Min Range: -6.0014

Max Act: 5.1151. Min Act: -0.0000

Data Index: 1285436 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 6.0014. Min Range: -6.0014

Max Act: 5.0425. Min Act: -0.0000

Data Index: 677146 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 6.0014. Min Range: -6.0014

Max Act: 4.6804. Min Act: -0.0000

Data Index: 492134 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.9252. Min Act: -0.0000

Data Index: 770038 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 6.0014. Min Range: -6.0014

Max Act: 4.3790. Min Act: -0.0000

Data Index: 911699 (C4 (Web Text))

Max Activating Token Index: 488

Text #7

Max Range: 6.0014. Min Range: -6.0014

Max Act: 4.4159. Min Act: -0.0000

Data Index: 374738 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.8393. Min Act: -0.0000

Data Index: 225026 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.7819. Min Act: -0.0000

Data Index: 1078326 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.9421. Min Act: -0.0000

Data Index: 1266645 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.9210. Min Act: -0.0000

Data Index: 656768 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.6601. Min Act: -0.0000

Data Index: 448065 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.8022. Min Act: -0.0000

Data Index: 572903 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.5597. Min Act: -0.0000

Data Index: 179678 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.5486. Min Act: -0.0000

Data Index: 379220 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.4191. Min Act: -0.0000

Data Index: 822058 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.2779. Min Act: -0.0000

Data Index: 941747 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.0358. Min Act: -0.0000

Data Index: 311425 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 6.0014. Min Range: -6.0014

Max Act: 3.4482. Min Act: -0.0000

Data Index: 536738 (C4 (Web Text))

Max Activating Token Index: 104