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

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

Neuron 2629 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.4813. Min Act: -0.0002

Data Index: 618114 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.3377. Min Act: -0.0002

Data Index: 8056 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.3236. Min Act: -0.0002

Data Index: 15648 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2779. Min Act: -0.0002

Data Index: 933981 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.3152. Min Act: -0.0002

Data Index: 698333 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2699. Min Act: -0.0002

Data Index: 264979 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2835. Min Act: -0.0002

Data Index: 362276 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2531. Min Act: -0.0002

Data Index: 1326955 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2132. Min Act: -0.0002

Data Index: 892018 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2508. Min Act: -0.0002

Data Index: 101210 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2278. Min Act: -0.0002

Data Index: 387154 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2358. Min Act: -0.0002

Data Index: 611257 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1869. Min Act: -0.0002

Data Index: 228867 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.2514. Min Act: -0.0002

Data Index: 267045 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1631. Min Act: -0.0002

Data Index: 1208070 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1989. Min Act: -0.0002

Data Index: 1286992 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1277. Min Act: -0.0002

Data Index: 659121 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1754. Min Act: -0.0002

Data Index: 446396 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1619. Min Act: -0.0002

Data Index: 400549 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.4813. Min Range: -1.4813

Max Act: 1.1519. Min Act: -0.0002

Data Index: 177467 (C4 (Web Text))

Max Activating Token Index: 107