Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 284 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0305. Min Act: -0.0004

Data Index: 487256 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0313. Min Act: -0.0004

Data Index: 219841 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0288. Min Act: -0.0004

Data Index: 1305960 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0254. Min Act: -0.0004

Data Index: 803269 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0282. Min Act: -0.0004

Data Index: 6386 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0262. Min Act: -0.0004

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0256. Min Act: -0.0004

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0242. Min Act: -0.0004

Data Index: 1252090 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0265. Min Act: -0.0004

Data Index: 611758 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0245. Min Act: -0.0004

Data Index: 1283447 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0255. Min Act: -0.0004

Data Index: 1077719 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0250. Min Act: -0.0004

Data Index: 1537751 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0262. Min Act: -0.0004

Data Index: 814527 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0248. Min Act: -0.0004

Data Index: 1153759 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0231. Min Act: -0.0004

Data Index: 607823 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0230. Min Act: -0.0004

Data Index: 1199968 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1341442 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0220. Min Act: -0.0004

Data Index: 55213 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0313. Min Range: -0.0313

Max Act: 0.0213. Min Act: -0.0004

Data Index: 1103323 (C4 (Web Text))

Max Activating Token Index: 871