Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 709 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0003

Data Index: 143021 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1189. Min Act: -0.0003

Data Index: 1179276 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1356300 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1157. Min Act: -0.0002

Data Index: 450668 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1128. Min Act: -0.0003

Data Index: 12403 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1077. Min Act: -0.0003

Data Index: 1137038 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1038. Min Act: -0.0003

Data Index: 102512 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1067. Min Act: -0.0003

Data Index: 409545 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1087. Min Act: -0.0002

Data Index: 458325 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1266217 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1281622 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1010. Min Act: -0.0003

Data Index: 144748 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0999. Min Act: -0.0003

Data Index: 535968 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0979. Min Act: -0.0003

Data Index: 273642 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0925. Min Act: -0.0003

Data Index: 1335787 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0920. Min Act: -0.0003

Data Index: 356947 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0950. Min Act: -0.0003

Data Index: 263751 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0900. Min Act: -0.0003

Data Index: 846374 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1260137 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0919. Min Act: -0.0003

Data Index: 1332217 (C4 (Web Text))

Max Activating Token Index: 137