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

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

Neuron 4691 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3136. Min Range: -5.3136

Max Act: 5.3051. Min Act: -0.0002

Data Index: 1033507 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 5.3136. Min Range: -5.3136

Max Act: 5.3027. Min Act: -0.0002

Data Index: 799092 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 5.3136. Min Range: -5.3136

Max Act: 5.3136. Min Act: -0.0002

Data Index: 1176835 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 5.3136. Min Range: -5.3136

Max Act: 5.1704. Min Act: -0.0002

Data Index: 418701 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 5.3136. Min Range: -5.3136

Max Act: 5.1310. Min Act: -0.0002

Data Index: 466256 (C4 (Web Text))

Max Activating Token Index: 984

Text #5

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.9282. Min Act: -0.0002

Data Index: 328294 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.8956. Min Act: -0.0002

Data Index: 267229 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.8571. Min Act: -0.0002

Data Index: 696491 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.8365. Min Act: -0.0002

Data Index: 272084 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.7885. Min Act: -0.0002

Data Index: 933906 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.6268. Min Act: -0.0002

Data Index: 860703 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 5.3136. Min Range: -5.3136

Max Act: 5.2171. Min Act: -0.0002

Data Index: 362079 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.8861. Min Act: -0.0002

Data Index: 1177503 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.8778. Min Act: -0.0002

Data Index: 765950 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.9908. Min Act: -0.0002

Data Index: 721295 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.6917. Min Act: -0.0002

Data Index: 1217775 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.4853. Min Act: -0.0002

Data Index: 40451 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.7908. Min Act: -0.0002

Data Index: 910575 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.5637. Min Act: -0.0002

Data Index: 208026 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 5.3136. Min Range: -5.3136

Max Act: 4.5465. Min Act: -0.0002

Data Index: 461535 (C4 (Web Text))

Max Activating Token Index: 608