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

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

Neuron 921 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1459. Min Act: -0.0000

Data Index: 242249 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1280. Min Act: -0.0001

Data Index: 857225 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1368. Min Act: -0.0000

Data Index: 639052 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1094993 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1355. Min Act: -0.0000

Data Index: 756529 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1274. Min Act: -0.0000

Data Index: 741921 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1176. Min Act: -0.0000

Data Index: 963550 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1266. Min Act: -0.0000

Data Index: 319217 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1330083 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1131. Min Act: -0.0001

Data Index: 448679 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1040744 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1096. Min Act: -0.0000

Data Index: 763335 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1124. Min Act: -0.0000

Data Index: 472874 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1123. Min Act: -0.0000

Data Index: 647391 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1116. Min Act: -0.0000

Data Index: 552241 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1094. Min Act: -0.0000

Data Index: 205326 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1092. Min Act: -0.0000

Data Index: 775977 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1053. Min Act: -0.0000

Data Index: 115386 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1085. Min Act: -0.0001

Data Index: 783322 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1036. Min Act: -0.0000

Data Index: 182146 (C4 (Web Text))

Max Activating Token Index: 328