Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4059 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0000

Data Index: 225759 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1351735 (The Pile)

Max Activating Token Index: 161

Text #2

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0270. Min Act: -0.0000

Data Index: 536098 (The Pile)

Max Activating Token Index: 431

Text #3

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1641457 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0260. Min Act: -0.0000

Data Index: 868671 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0267. Min Act: -0.0000

Data Index: 1191366 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1722533 (The Pile)

Max Activating Token Index: 226

Text #7

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0252. Min Act: -0.0000

Data Index: 1197844 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0252. Min Act: -0.0000

Data Index: 1108715 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0252. Min Act: -0.0000

Data Index: 252216 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1118371 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0240. Min Act: -0.0000

Data Index: 797112 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0248. Min Act: -0.0000

Data Index: 1941846 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0248. Min Act: -0.0000

Data Index: 893583 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0246. Min Act: -0.0000

Data Index: 1651614 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0244. Min Act: -0.0000

Data Index: 259935 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1967735 (The Pile)

Max Activating Token Index: 412

Text #17

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0239. Min Act: -0.0000

Data Index: 1252371 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0250. Min Act: -0.0000

Data Index: 1397742 (The Pile)

Max Activating Token Index: 158

Text #19

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1858334 (The Pile)

Max Activating Token Index: 397