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

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

Neuron 5502 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: 0.0358. Min Range: -0.0358

Max Act: 0.0358. Min Act: -0.0001

Data Index: 627675 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0312. Min Act: -0.0001

Data Index: 804596 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0296. Min Act: -0.0001

Data Index: 707214 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1550423 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0289. Min Act: -0.0001

Data Index: 346672 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1151731 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1127169 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0284. Min Act: -0.0001

Data Index: 1479198 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0256. Min Act: -0.0001

Data Index: 403385 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0275. Min Act: -0.0001

Data Index: 1375609 (Python Code)

Max Activating Token Index: 613

Text #10

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1512531 (Python Code)

Max Activating Token Index: 203

Text #11

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1488263 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0284. Min Act: -0.0001

Data Index: 606989 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1467444 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0262. Min Act: -0.0001

Data Index: 794761 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0266. Min Act: -0.0001

Data Index: 933969 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0270. Min Act: -0.0001

Data Index: 814625 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0276. Min Act: -0.0001

Data Index: 364368 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1090007 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0281. Min Act: -0.0001

Data Index: 765056 (C4 (Web Text))

Max Activating Token Index: 976