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

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

Neuron 1418 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: 0.0048. Min Range: -0.0048

Max Act: 0.0048. Min Act: -0.0006

Data Index: 531906 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0006

Data Index: 1571996 (Python Code)

Max Activating Token Index: 986

Text #2

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 831439 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 1326127 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0006

Data Index: 469821 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 1253302 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 936010 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0044. Min Act: -0.0007

Data Index: 879102 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 770822 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 141832 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 521650 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 913949 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0043. Min Act: -0.0006

Data Index: 1609760 (Python Code)

Max Activating Token Index: 1020

Text #13

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 360827 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 286080 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 485571 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 677495 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0005

Data Index: 7063 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0041. Min Act: -0.0006

Data Index: 380446 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.0048. Min Range: -0.0048

Max Act: 0.0042. Min Act: -0.0006

Data Index: 1150575 (C4 (Web Text))

Max Activating Token Index: 324