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

Dataset: The Pile

Neuron 2596 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: 0.0195. Min Range: -0.0195

Max Act: 0.0193. Min Act: -0.0000

Data Index: 1033041 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: 0.0001

Data Index: 378446 (The Pile)

Max Activating Token Index: 817

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0000

Data Index: 974030 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0183. Min Act: -0.0000

Data Index: 320724 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0183. Min Act: -0.0000

Data Index: 1483129 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0176. Min Act: -0.0001

Data Index: 1829598 (The Pile)

Max Activating Token Index: 528

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0176. Min Act: -0.0000

Data Index: 1394306 (The Pile)

Max Activating Token Index: 21

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0175. Min Act: -0.0000

Data Index: 1218037 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0173. Min Act: -0.0000

Data Index: 451789 (The Pile)

Max Activating Token Index: 158

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0172. Min Act: -0.0000

Data Index: 500761 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0000

Data Index: 1038577 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0000

Data Index: 366625 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0000

Data Index: 377482 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0000

Data Index: 133830 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0167. Min Act: -0.0000

Data Index: 704235 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0166. Min Act: -0.0000

Data Index: 232060 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0164. Min Act: -0.0000

Data Index: 1241927 (The Pile)

Max Activating Token Index: 363

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0165. Min Act: -0.0000

Data Index: 1158357 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0165. Min Act: -0.0000

Data Index: 524520 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0000

Data Index: 852389 (The Pile)

Max Activating Token Index: 179