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

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

Neuron 525 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: 0.0271. Min Range: -0.0271

Max Act: 0.0271. Min Act: -0.0004

Data Index: 982422 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0270. Min Act: -0.0004

Data Index: 303297 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0258. Min Act: -0.0004

Data Index: 295574 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0253. Min Act: -0.0004

Data Index: 337597 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0268. Min Act: -0.0004

Data Index: 641154 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0260. Min Act: -0.0004

Data Index: 348469 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0245. Min Act: -0.0004

Data Index: 1041341 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0254. Min Act: -0.0004

Data Index: 3587 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0259. Min Act: -0.0004

Data Index: 29985 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1196743 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0252. Min Act: -0.0004

Data Index: 738129 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0220. Min Act: -0.0004

Data Index: 545485 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0261. Min Act: -0.0004

Data Index: 136898 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0238. Min Act: -0.0004

Data Index: 484254 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0220. Min Act: -0.0004

Data Index: 407343 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0237. Min Act: -0.0004

Data Index: 989214 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0253. Min Act: -0.0004

Data Index: 994311 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1244200 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0217. Min Act: -0.0004

Data Index: 252049 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.0271. Min Range: -0.0271

Max Act: 0.0227. Min Act: -0.0004

Data Index: 218084 (C4 (Web Text))

Max Activating Token Index: 955