Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 532 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0300. Min Act: -0.0006

Data Index: 534734 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0303. Min Act: -0.0006

Data Index: 487673 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0304. Min Act: -0.0006

Data Index: 876689 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1157322 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0256. Min Act: -0.0006

Data Index: 138384 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0269. Min Act: -0.0006

Data Index: 466765 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0227. Min Act: -0.0006

Data Index: 1010030 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0265. Min Act: -0.0006

Data Index: 1304200 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0274. Min Act: -0.0006

Data Index: 774696 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1047020 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0274. Min Act: -0.0006

Data Index: 225327 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0284. Min Act: -0.0006

Data Index: 564875 (C4 (Web Text))

Max Activating Token Index: 519

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0266. Min Act: -0.0006

Data Index: 121710 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0238. Min Act: -0.0006

Data Index: 26144 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0291. Min Act: -0.0006

Data Index: 966041 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0256. Min Act: -0.0006

Data Index: 979571 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1123041 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0248. Min Act: -0.0006

Data Index: 124084 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1193887 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0241. Min Act: -0.0006

Data Index: 444012 (C4 (Web Text))

Max Activating Token Index: 120