Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2761 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0393. Min Act: -0.0003

Data Index: 109136 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1352007 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0357. Min Act: -0.0003

Data Index: 412647 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0358. Min Act: -0.0004

Data Index: 233609 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0331. Min Act: -0.0003

Data Index: 469173 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0288. Min Act: -0.0004

Data Index: 759987 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0343. Min Act: -0.0004

Data Index: 1284706 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0340. Min Act: -0.0003

Data Index: 799347 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0303. Min Act: -0.0003

Data Index: 961477 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0317. Min Act: -0.0003

Data Index: 52036 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1355280 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0323. Min Act: -0.0003

Data Index: 222842 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1440587 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0306. Min Act: -0.0003

Data Index: 1353318 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0277. Min Act: -0.0004

Data Index: 14409 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0304. Min Act: -0.0003

Data Index: 278991 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0333. Min Act: -0.0003

Data Index: 931440 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0319. Min Act: -0.0003

Data Index: 957646 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0311. Min Act: -0.0003

Data Index: 138917 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.0393. Min Range: -0.0393

Max Act: 0.0294. Min Act: -0.0003

Data Index: 891195 (C4 (Web Text))

Max Activating Token Index: 585