Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 538 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0040. Min Act: -0.0003

Data Index: 875255 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0040. Min Act: -0.0003

Data Index: 392430 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0040. Min Act: -0.0003

Data Index: 127520 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0040. Min Act: -0.0003

Data Index: 296350 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 422370 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 440985 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 821553 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 200810 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 438827 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 858991 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 739588 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 329920 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 719574 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0002

Data Index: 289473 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1080722 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0038. Min Act: -0.0003

Data Index: 618253 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0002

Data Index: 1336185 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 585639 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0003

Data Index: 100724 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.0040. Min Range: -0.0040

Max Act: 0.0039. Min Act: -0.0002

Data Index: 730541 (C4 (Web Text))

Max Activating Token Index: 814