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

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

Neuron 217 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: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1205800 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0100. Min Act: -0.0006

Data Index: 762207 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0006

Data Index: 768937 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0006

Data Index: 756081 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0006

Data Index: 476878 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0098. Min Act: -0.0006

Data Index: 304433 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1038585 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1169867 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0100. Min Act: -0.0006

Data Index: 457132 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0006

Data Index: 218825 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0099. Min Act: -0.0006

Data Index: 968493 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0006

Data Index: 660014 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0006

Data Index: 831857 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0096. Min Act: -0.0006

Data Index: 893605 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0093. Min Act: -0.0006

Data Index: 549482 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0006

Data Index: 201835 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: -0.0006

Data Index: 142305 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0006

Data Index: 276499 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0006

Data Index: 484637 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0006

Data Index: 796826 (C4 (Web Text))

Max Activating Token Index: 840