Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2238 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0000

Data Index: 557428 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1358. Min Act: -0.0000

Data Index: 915708 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1345. Min Act: -0.0000

Data Index: 588350 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1248. Min Act: -0.0000

Data Index: 202188 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1183. Min Act: -0.0000

Data Index: 69792 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1176. Min Act: -0.0000

Data Index: 855445 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1111285 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1072. Min Act: -0.0000

Data Index: 220443 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1081. Min Act: -0.0000

Data Index: 834826 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1110. Min Act: -0.0000

Data Index: 143774 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1114. Min Act: -0.0000

Data Index: 232688 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1094. Min Act: -0.0000

Data Index: 266878 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1080. Min Act: -0.0000

Data Index: 299279 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.0997. Min Act: -0.0000

Data Index: 62049 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1067. Min Act: -0.0000

Data Index: 908094 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1075. Min Act: -0.0000

Data Index: 155227 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1032. Min Act: -0.0000

Data Index: 51318 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1031. Min Act: -0.0000

Data Index: 333980 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1069. Min Act: -0.0000

Data Index: 1045958 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1136491 (C4 (Web Text))

Max Activating Token Index: 903