Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2615 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1220. Min Act: -0.0004

Data Index: 1333738 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1128. Min Act: -0.0004

Data Index: 548355 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1155. Min Act: -0.0003

Data Index: 200354 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1087. Min Act: -0.0003

Data Index: 290427 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1161. Min Act: -0.0004

Data Index: 372011 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1110. Min Act: -0.0004

Data Index: 476230 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1146. Min Act: -0.0004

Data Index: 108126 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1135. Min Act: -0.0003

Data Index: 1135034 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1165. Min Act: -0.0004

Data Index: 1072119 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1047. Min Act: -0.0004

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1041. Min Act: -0.0004

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1114. Min Act: -0.0004

Data Index: 194132 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1075. Min Act: -0.0003

Data Index: 367599 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1069. Min Act: -0.0004

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1107. Min Act: -0.0004

Data Index: 282103 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1011. Min Act: -0.0004

Data Index: 1073687 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1013. Min Act: -0.0004

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0951. Min Act: -0.0004

Data Index: 496512 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1059. Min Act: -0.0003

Data Index: 109311 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1014. Min Act: -0.0004

Data Index: 419794 (C4 (Web Text))

Max Activating Token Index: 224