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

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

Neuron 2321 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1157454 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0353. Min Act: -0.0001

Data Index: 776786 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0304. Min Act: -0.0001

Data Index: 108151 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0293. Min Act: -0.0001

Data Index: 662941 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0269. Min Act: -0.0000

Data Index: 901150 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0266. Min Act: -0.0000

Data Index: 255546 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0275. Min Act: -0.0001

Data Index: 948616 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0254. Min Act: -0.0000

Data Index: 820516 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1545665 (Python Code)

Max Activating Token Index: 328

Text #9

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0239. Min Act: -0.0001

Data Index: 455328 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0260. Min Act: -0.0001

Data Index: 813645 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1622900 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0257. Min Act: -0.0000

Data Index: 98807 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1083732 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0236. Min Act: -0.0001

Data Index: 935064 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1415631 (Python Code)

Max Activating Token Index: 699

Text #16

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0222. Min Act: -0.0001

Data Index: 622236 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0223. Min Act: -0.0001

Data Index: 816141 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0204. Min Act: -0.0001

Data Index: 51913 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0353. Min Range: -0.0353

Max Act: 0.0223. Min Act: -0.0001

Data Index: 739034 (C4 (Web Text))

Max Activating Token Index: 819