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

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

Neuron 3840 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0296. Min Act: -0.0003

Data Index: 531605 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0288. Min Act: -0.0003

Data Index: 258841 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0290. Min Act: -0.0003

Data Index: 686364 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0273. Min Act: -0.0004

Data Index: 1256237 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0268. Min Act: -0.0003

Data Index: 987009 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0258. Min Act: -0.0003

Data Index: 538836 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0280. Min Act: -0.0003

Data Index: 471463 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0262. Min Act: -0.0003

Data Index: 463986 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0262. Min Act: -0.0003

Data Index: 564515 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0260. Min Act: -0.0003

Data Index: 1198123 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0254. Min Act: -0.0003

Data Index: 8922 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0231. Min Act: -0.0003

Data Index: 698531 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0246. Min Act: -0.0003

Data Index: 646255 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0242. Min Act: -0.0003

Data Index: 218993 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0257. Min Act: -0.0004

Data Index: 407529 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1070513 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0262. Min Act: -0.0003

Data Index: 421482 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0258. Min Act: -0.0003

Data Index: 990762 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0234. Min Act: -0.0003

Data Index: 528675 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.0296. Min Range: -0.0296

Max Act: 0.0248. Min Act: -0.0003

Data Index: 782852 (C4 (Web Text))

Max Activating Token Index: 109