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

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

Neuron 40 in Layer 8

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: 0.0347. Min Act: -0.0000

Data Index: 1013299 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0358. Min Act: -0.0000

Data Index: 559070 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0345. Min Act: -0.0000

Data Index: 1620346 (Python Code)

Max Activating Token Index: 438

Text #3

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0306. Min Act: -0.0000

Data Index: 81612 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1601349 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0289. Min Act: -0.0000

Data Index: 636011 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0296. Min Act: -0.0000

Data Index: 1328061 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0290. Min Act: -0.0000

Data Index: 804679 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0279. Min Act: -0.0000

Data Index: 119315 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1642980 (Python Code)

Max Activating Token Index: 291

Text #10

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1385592 (Python Code)

Max Activating Token Index: 188

Text #11

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0253. Min Act: -0.0000

Data Index: 503532 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0260. Min Act: -0.0000

Data Index: 427613 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0249. Min Act: -0.0000

Data Index: 572072 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0255. Min Act: -0.0000

Data Index: 772166 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0248. Min Act: -0.0000

Data Index: 845004 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0239. Min Act: -0.0000

Data Index: 864639 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0250. Min Act: -0.0000

Data Index: 1389363 (Python Code)

Max Activating Token Index: 800

Text #18

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0228. Min Act: -0.0000

Data Index: 340574 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0258. Min Act: -0.0000

Data Index: 750811 (C4 (Web Text))

Max Activating Token Index: 594