Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2809 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1196. Min Act: -0.0000

Data Index: 429288 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1999872 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1264. Min Act: -0.0000

Data Index: 46820 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1214136 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1284. Min Act: -0.0000

Data Index: 618886 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1378227 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1179. Min Act: -0.0000

Data Index: 563610 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1332. Min Act: -0.0000

Data Index: 541365 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1132. Min Act: -0.0000

Data Index: 524282 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1586188 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1735322 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1114. Min Act: -0.0000

Data Index: 891393 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1168. Min Act: -0.0000

Data Index: 1559455 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1572442 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1239. Min Act: -0.0000

Data Index: 781672 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1713828 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1190. Min Act: -0.0000

Data Index: 787824 (The Pile)

Max Activating Token Index: 40

Text #17

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1107. Min Act: -0.0000

Data Index: 591006 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1258. Min Act: -0.0000

Data Index: 1145781 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 0.1337. Min Range: -0.1337

Max Act: 0.1129. Min Act: -0.0000

Data Index: 1714179 (The Pile)

Max Activating Token Index: 229