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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1233. Min Act: -0.0002

Data Index: 1187653 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1364. Min Act: -0.0002

Data Index: 434090 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1197. Min Act: -0.0002

Data Index: 739501 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1190. Min Act: -0.0002

Data Index: 470309 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1339668 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1254. Min Act: -0.0002

Data Index: 633193 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1096103 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1061. Min Act: -0.0002

Data Index: 1355660 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1028. Min Act: -0.0002

Data Index: 304269 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0920. Min Act: -0.0002

Data Index: 981468 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1062969 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1177. Min Act: -0.0002

Data Index: 1306002 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1058. Min Act: -0.0002

Data Index: 920616 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1133. Min Act: -0.0002

Data Index: 686254 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1298953 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1094451 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0991. Min Act: -0.0002

Data Index: 113226 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0982. Min Act: -0.0002

Data Index: 681323 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1121. Min Act: -0.0002

Data Index: 598920 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0973. Min Act: -0.0002

Data Index: 993192 (C4 (Web Text))

Max Activating Token Index: 223