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

Dataset: The Pile

Neuron 814 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1315. Min Act: -0.0000

Data Index: 275755 (The Pile)

Max Activating Token Index: 173

Text #1

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1393. Min Act: -0.0000

Data Index: 1946365 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1830112 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1210995 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1289. Min Act: -0.0000

Data Index: 614248 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1323. Min Act: -0.0000

Data Index: 275185 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1316. Min Act: -0.0000

Data Index: 99020 (The Pile)

Max Activating Token Index: 584

Text #7

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1216. Min Act: -0.0000

Data Index: 1647962 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1234. Min Act: -0.0000

Data Index: 61659 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1367574 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1404137 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1239. Min Act: -0.0000

Data Index: 940386 (The Pile)

Max Activating Token Index: 28

Text #12

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1210. Min Act: -0.0000

Data Index: 674186 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1173690 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1181. Min Act: -0.0000

Data Index: 589690 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1178. Min Act: -0.0000

Data Index: 1861228 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1176. Min Act: -0.0000

Data Index: 1704360 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1747039 (The Pile)

Max Activating Token Index: 85

Text #18

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1818243 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1161. Min Act: -0.0000

Data Index: 514370 (The Pile)

Max Activating Token Index: 552