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

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

Neuron 1318 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: 3.9687. Min Range: -3.9687

Max Act: 3.9687. Min Act: -0.0000

Data Index: 824687 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.7999. Min Act: -0.0000

Data Index: 324878 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.9020. Min Act: -0.0000

Data Index: 1138163 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.5805. Min Act: -0.0000

Data Index: 1283188 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.5733. Min Act: -0.0000

Data Index: 817768 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.4169. Min Act: -0.0000

Data Index: 848166 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.3534. Min Act: -0.0000

Data Index: 84808 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.3356. Min Act: -0.0000

Data Index: 200970 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.1110. Min Act: -0.0000

Data Index: 291031 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.2185. Min Act: -0.0000

Data Index: 1042190 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.0259. Min Act: -0.0000

Data Index: 716204 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.6922. Min Act: -0.0000

Data Index: 873064 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.1481. Min Act: -0.0000

Data Index: 390727 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.0931. Min Act: -0.0000

Data Index: 90518 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.9342. Min Act: -0.0000

Data Index: 58274 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.9784. Min Act: -0.0000

Data Index: 530695 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.8112. Min Act: -0.0000

Data Index: 423641 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 3.9687. Min Range: -3.9687

Max Act: 3.0570. Min Act: -0.0000

Data Index: 998833 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.7811. Min Act: -0.0000

Data Index: 251937 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 3.9687. Min Range: -3.9687

Max Act: 2.6295. Min Act: -0.0000

Data Index: 1261805 (C4 (Web Text))

Max Activating Token Index: 367