Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1502 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1337591 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0397. Min Act: -0.0003

Data Index: 970680 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0393. Min Act: -0.0003

Data Index: 270279 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0407. Min Act: -0.0003

Data Index: 390703 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0434. Min Act: -0.0003

Data Index: 907806 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1359115 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0414. Min Act: -0.0003

Data Index: 41594 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0311. Min Act: -0.0003

Data Index: 439583 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0303. Min Act: -0.0003

Data Index: 841871 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0362. Min Act: -0.0003

Data Index: 405143 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0380. Min Act: -0.0003

Data Index: 171995 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0306. Min Act: -0.0003

Data Index: 126386 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0360. Min Act: -0.0003

Data Index: 157991 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0277. Min Act: -0.0003

Data Index: 614694 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0358. Min Act: -0.0003

Data Index: 997743 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0341. Min Act: -0.0003

Data Index: 531056 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0364. Min Act: -0.0003

Data Index: 393429 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0326. Min Act: -0.0003

Data Index: 76625 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0340. Min Act: -0.0003

Data Index: 34770 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0471. Min Range: -0.0471

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1303148 (C4 (Web Text))

Max Activating Token Index: 240