Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0301. Min Act: -0.0006

Data Index: 605577 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0296. Min Act: -0.0006

Data Index: 903040 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1005163 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0279. Min Act: -0.0006

Data Index: 1194624 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0268. Min Act: -0.0006

Data Index: 201622 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0263. Min Act: -0.0006

Data Index: 735607 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0259. Min Act: -0.0006

Data Index: 551234 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1318191 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0253. Min Act: -0.0006

Data Index: 318257 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0264. Min Act: -0.0006

Data Index: 1080643 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1341832 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0251. Min Act: -0.0006

Data Index: 310213 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0254. Min Act: -0.0006

Data Index: 393846 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0253. Min Act: -0.0006

Data Index: 321825 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0253. Min Act: -0.0006

Data Index: 488173 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0254. Min Act: -0.0006

Data Index: 987796 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0247. Min Act: -0.0006

Data Index: 203080 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0239. Min Act: -0.0006

Data Index: 439243 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1323821 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0301. Min Range: -0.0301

Max Act: 0.0253. Min Act: -0.0006

Data Index: 115989 (C4 (Web Text))

Max Activating Token Index: 694