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

Dataset: The Pile

Neuron 2649 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: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1926432 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1258. Min Act: -0.0000

Data Index: 8816 (The Pile)

Max Activating Token Index: 214

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1660756 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1076. Min Act: -0.0000

Data Index: 462884 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1186. Min Act: -0.0000

Data Index: 13940 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1632580 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1149. Min Act: -0.0000

Data Index: 393160 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1125. Min Act: -0.0000

Data Index: 983366 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1076. Min Act: -0.0000

Data Index: 384050 (The Pile)

Max Activating Token Index: 382

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1036. Min Act: -0.0000

Data Index: 1847611 (The Pile)

Max Activating Token Index: 772

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0988. Min Act: -0.0000

Data Index: 758455 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1437844 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1964334 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1002. Min Act: -0.0000

Data Index: 613548 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1105. Min Act: -0.0000

Data Index: 908462 (The Pile)

Max Activating Token Index: 73

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1028. Min Act: -0.0000

Data Index: 801759 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1065. Min Act: -0.0000

Data Index: 497102 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1241323 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0978. Min Act: -0.0000

Data Index: 502791 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1506006 (The Pile)

Max Activating Token Index: 102