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

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

Neuron 4088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0000

Data Index: 532760 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1221446 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1499854 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0296. Min Act: -0.0000

Data Index: 720673 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0260. Min Act: -0.0000

Data Index: 399296 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0246. Min Act: -0.0000

Data Index: 704167 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0265. Min Act: -0.0000

Data Index: 225243 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0253. Min Act: -0.0000

Data Index: 60477 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0273. Min Act: -0.0000

Data Index: 940131 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0250. Min Act: -0.0000

Data Index: 679406 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0247. Min Act: -0.0000

Data Index: 97097 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1389582 (Python Code)

Max Activating Token Index: 798

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0252. Min Act: -0.0000

Data Index: 387612 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0257. Min Act: -0.0000

Data Index: 471233 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0229. Min Act: -0.0000

Data Index: 1011823 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0228. Min Act: -0.0000

Data Index: 364826 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0241. Min Act: -0.0000

Data Index: 844098 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0237. Min Act: -0.0000

Data Index: 1585434 (Python Code)

Max Activating Token Index: 103

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0226. Min Act: -0.0000

Data Index: 568358 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0201. Min Act: -0.0000

Data Index: 1460114 (Python Code)

Max Activating Token Index: 657