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

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

Neuron 1226 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: 0.0097. Min Act: -0.0006

Data Index: 1599372 (Python Code)

Max Activating Token Index: 531

Text #1

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0006

Data Index: 471169 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1494784 (Python Code)

Max Activating Token Index: 967

Text #3

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0092. Min Act: -0.0006

Data Index: 46200 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0006

Data Index: 145889 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0088. Min Act: -0.0006

Data Index: 371319 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0087. Min Act: -0.0006

Data Index: 874228 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1063492 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1411130 (Python Code)

Max Activating Token Index: 433

Text #9

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1000260 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0083. Min Act: -0.0006

Data Index: 856809 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 752656 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 449470 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 63409 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1451093 (Python Code)

Max Activating Token Index: 24

Text #15

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0078. Min Act: -0.0006

Data Index: 111402 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0077. Min Act: -0.0006

Data Index: 317082 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1091051 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1289906 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1121388 (C4 (Web Text))

Max Activating Token Index: 796