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

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

Neuron 4035 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1107. Min Act: -0.0003

Data Index: 1474918 (Python Code)

Max Activating Token Index: 925

Text #1

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0988. Min Act: -0.0003

Data Index: 558732 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1091. Min Act: -0.0003

Data Index: 1391340 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0840. Min Act: -0.0003

Data Index: 1286907 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0997. Min Act: -0.0003

Data Index: 772386 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0993. Min Act: -0.0003

Data Index: 957689 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1132. Min Act: -0.0003

Data Index: 195276 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1092. Min Act: -0.0003

Data Index: 1281502 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1084. Min Act: -0.0003

Data Index: 836615 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1006. Min Act: -0.0003

Data Index: 491074 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1155. Min Act: -0.0003

Data Index: 1587306 (Python Code)

Max Activating Token Index: 190

Text #11

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1127. Min Act: -0.0003

Data Index: 1434299 (Python Code)

Max Activating Token Index: 955

Text #12

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1394639 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1158. Min Act: -0.0003

Data Index: 1229105 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1015. Min Act: -0.0003

Data Index: 409072 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.0889. Min Act: -0.0003

Data Index: 525475 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1009. Min Act: -0.0003

Data Index: 663129 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1084. Min Act: -0.0003

Data Index: 854779 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1084. Min Act: -0.0003

Data Index: 200130 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.1158. Min Range: -0.1158

Max Act: 0.1005. Min Act: -0.0003

Data Index: 1479842 (Python Code)

Max Activating Token Index: 239