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

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

Neuron 1090 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: 0.0309. Min Range: -0.0309

Max Act: 0.0297. Min Act: -0.0006

Data Index: 142713 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0006

Data Index: 365334 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0286. Min Act: -0.0006

Data Index: 795778 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0267. Min Act: -0.0006

Data Index: 1073032 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0279. Min Act: -0.0006

Data Index: 31158 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0274. Min Act: -0.0005

Data Index: 518411 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0261. Min Act: -0.0006

Data Index: 1222453 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0254. Min Act: -0.0006

Data Index: 739133 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0265. Min Act: -0.0006

Data Index: 370951 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0276. Min Act: -0.0006

Data Index: 1008804 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0256. Min Act: -0.0006

Data Index: 1184727 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0253. Min Act: -0.0006

Data Index: 926045 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0246. Min Act: -0.0006

Data Index: 1285081 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0263. Min Act: -0.0006

Data Index: 570990 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0257. Min Act: -0.0006

Data Index: 704782 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0242. Min Act: -0.0006

Data Index: 469699 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0249. Min Act: -0.0006

Data Index: 934318 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1546397 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0253. Min Act: -0.0006

Data Index: 398995 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0257. Min Act: -0.0006

Data Index: 1317351 (C4 (Web Text))

Max Activating Token Index: 691