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

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

Neuron 167 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1377. Min Act: -0.0003

Data Index: 1156687 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1227. Min Act: -0.0002

Data Index: 578292 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1207. Min Act: -0.0002

Data Index: 941704 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1176. Min Act: -0.0002

Data Index: 1255257 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1148. Min Act: -0.0003

Data Index: 291353 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1075. Min Act: -0.0002

Data Index: 443729 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1227243 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1106. Min Act: -0.0002

Data Index: 798945 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1087. Min Act: -0.0002

Data Index: 614254 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1094. Min Act: -0.0003

Data Index: 875248 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1108. Min Act: -0.0002

Data Index: 738419 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1056. Min Act: -0.0003

Data Index: 26667 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1066. Min Act: -0.0003

Data Index: 196289 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1045. Min Act: -0.0002

Data Index: 46255 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1048. Min Act: -0.0002

Data Index: 248410 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1047. Min Act: -0.0002

Data Index: 797433 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1291917 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1038. Min Act: -0.0002

Data Index: 717540 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.1028. Min Act: -0.0002

Data Index: 987927 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.1377. Min Range: -0.1377

Max Act: 0.0977. Min Act: -0.0002

Data Index: 627673 (C4 (Web Text))

Max Activating Token Index: 662