Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1549 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3372. Min Act: -0.0000

Data Index: 469728 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1109289 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2615. Min Act: -0.0000

Data Index: 106981 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2374. Min Act: -0.0000

Data Index: 662795 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2479. Min Act: 0.0000

Data Index: 743326 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2312. Min Act: -0.0000

Data Index: 217756 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2375. Min Act: -0.0000

Data Index: 67501 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2440. Min Act: -0.0000

Data Index: 732706 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2508. Min Act: -0.0000

Data Index: 213869 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2377. Min Act: -0.0000

Data Index: 811281 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2416. Min Act: -0.0000

Data Index: 82888 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2317. Min Act: -0.0000

Data Index: 1168509 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2217. Min Act: -0.0000

Data Index: 775564 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2349. Min Act: -0.0000

Data Index: 1264958 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2350. Min Act: -0.0000

Data Index: 129237 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2246. Min Act: -0.0000

Data Index: 173191 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2304. Min Act: -0.0000

Data Index: 529090 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2190. Min Act: -0.0000

Data Index: 735305 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1012043 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2166. Min Act: -0.0000

Data Index: 136738 (C4 (Web Text))

Max Activating Token Index: 995