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

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

Neuron 349 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.8817. Min Act: -0.0000

Data Index: 1269395 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1147643 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1027098 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1615932 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.6724. Min Act: -0.0000

Data Index: 309039 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.6155. Min Act: -0.0000

Data Index: 938138 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5332. Min Act: -0.0000

Data Index: 912880 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1545436 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1393022 (Python Code)

Max Activating Token Index: 447

Text #9

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1434117 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5055. Min Act: -0.0000

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5162. Min Act: -0.0000

Data Index: 542187 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4818. Min Act: -0.0000

Data Index: 493581 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4813. Min Act: -0.0000

Data Index: 87667 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1415503 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1532462 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1636275 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4716. Min Act: -0.0000

Data Index: 455471 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1179168 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4934. Min Act: -0.0000

Data Index: 177697 (C4 (Web Text))

Max Activating Token Index: 180