Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1524 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0006

Data Index: 173739 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0096. Min Act: -0.0006

Data Index: 405555 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1001835 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0087. Min Act: -0.0006

Data Index: 280043 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0083. Min Act: -0.0006

Data Index: 714045 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0083. Min Act: -0.0006

Data Index: 375829 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0084. Min Act: -0.0006

Data Index: 319189 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1123098 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 414151 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 311861 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1447362 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 278290 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 680058 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1413581 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1086744 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1184968 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0077. Min Act: -0.0006

Data Index: 461694 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0078. Min Act: -0.0006

Data Index: 150992 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1210934 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0078. Min Act: -0.0007

Data Index: 1195227 (C4 (Web Text))

Max Activating Token Index: 272