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

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

Neuron 4001 in Layer 3

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: 0.0295. Min Act: -0.0001

Data Index: 609806 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0287. Min Act: -0.0001

Data Index: 222262 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0307. Min Act: -0.0001

Data Index: 765292 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0259. Min Act: -0.0001

Data Index: 407530 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0293. Min Act: -0.0001

Data Index: 376499 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0291. Min Act: -0.0001

Data Index: 143960 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0286. Min Act: -0.0001

Data Index: 436967 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0276. Min Act: -0.0001

Data Index: 598580 (C4 (Web Text))

Max Activating Token Index: 573

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0294. Min Act: -0.0001

Data Index: 487421 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0277. Min Act: -0.0001

Data Index: 820617 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0285. Min Act: -0.0001

Data Index: 278686 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1490267 (Python Code)

Max Activating Token Index: 700

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0283. Min Act: -0.0001

Data Index: 351537 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0272. Min Act: -0.0001

Data Index: 47982 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0001

Data Index: 381076 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0299. Min Act: -0.0001

Data Index: 890769 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1254752 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0250. Min Act: -0.0001

Data Index: 264686 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0276. Min Act: -0.0001

Data Index: 607657 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0241. Min Act: -0.0001

Data Index: 698610 (C4 (Web Text))

Max Activating Token Index: 381