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

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

Neuron 1502 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0003

Data Index: 574309 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0324. Min Act: -0.0002

Data Index: 64025 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0321. Min Act: -0.0003

Data Index: 164292 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0307. Min Act: -0.0003

Data Index: 54474 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0299. Min Act: -0.0002

Data Index: 498780 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0294. Min Act: -0.0003

Data Index: 827423 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0293. Min Act: -0.0003

Data Index: 609018 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0263. Min Act: -0.0002

Data Index: 74272 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1334069 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0251. Min Act: -0.0003

Data Index: 722596 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1329142 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0245. Min Act: -0.0002

Data Index: 145824 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1329098 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0242. Min Act: -0.0003

Data Index: 332372 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0240. Min Act: -0.0002

Data Index: 593912 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0238. Min Act: -0.0003

Data Index: 140805 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0242. Min Act: -0.0002

Data Index: 670000 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0232. Min Act: -0.0003

Data Index: 429335 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0235. Min Act: -0.0003

Data Index: 985260 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1267675 (C4 (Web Text))

Max Activating Token Index: 1022