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

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

Neuron 2642 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0003

Data Index: 939606 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0283. Min Act: -0.0002

Data Index: 249340 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0316. Min Act: -0.0003

Data Index: 176847 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0296. Min Act: -0.0003

Data Index: 292183 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0300. Min Act: -0.0003

Data Index: 962323 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0297. Min Act: -0.0003

Data Index: 530405 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1406247 (Python Code)

Max Activating Token Index: 303

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0276. Min Act: -0.0003

Data Index: 819199 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1372841 (Python Code)

Max Activating Token Index: 755

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1060039 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1426111 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1255150 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0270. Min Act: -0.0003

Data Index: 322112 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1446313 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0273. Min Act: -0.0003

Data Index: 961140 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0258. Min Act: -0.0003

Data Index: 508646 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1493019 (Python Code)

Max Activating Token Index: 603

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0274. Min Act: -0.0003

Data Index: 98246 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0262. Min Act: -0.0003

Data Index: 530014 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1561950 (Python Code)

Max Activating Token Index: 632