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

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

Neuron 2263 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0000

Data Index: 859345 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1451. Min Act: -0.0000

Data Index: 1132391 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1439. Min Act: -0.0000

Data Index: 348180 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1294. Min Act: -0.0000

Data Index: 316878 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1356. Min Act: -0.0000

Data Index: 174225 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1104164 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1231. Min Act: -0.0000

Data Index: 976254 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1346. Min Act: -0.0000

Data Index: 825414 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1213. Min Act: -0.0000

Data Index: 757290 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1183. Min Act: -0.0000

Data Index: 594641 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1139. Min Act: -0.0000

Data Index: 754712 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1146723 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1132. Min Act: -0.0000

Data Index: 245155 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1048. Min Act: -0.0000

Data Index: 887607 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1110. Min Act: -0.0000

Data Index: 703058 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1010047 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1137. Min Act: -0.0000

Data Index: 157919 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1042. Min Act: -0.0000

Data Index: 724746 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1057. Min Act: -0.0000

Data Index: 360370 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1052. Min Act: -0.0000

Data Index: 727613 (C4 (Web Text))

Max Activating Token Index: 139