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

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

Neuron 2055 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.7077. Min Act: -0.0003

Data Index: 518392 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.6019. Min Act: -0.0003

Data Index: 177959 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5847. Min Act: -0.0003

Data Index: 1036485 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5507. Min Act: -0.0003

Data Index: 814169 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5080. Min Act: -0.0003

Data Index: 1286280 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.4794. Min Act: -0.0003

Data Index: 925812 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5643. Min Act: -0.0003

Data Index: 480725 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5814. Min Act: -0.0003

Data Index: 1177391 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5814. Min Act: -0.0003

Data Index: 547466 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5644. Min Act: -0.0003

Data Index: 1113635 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5390. Min Act: -0.0003

Data Index: 37641 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.6079. Min Act: -0.0003

Data Index: 782249 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5157. Min Act: -0.0003

Data Index: 370701 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5286. Min Act: -0.0003

Data Index: 601642 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5622. Min Act: -0.0004

Data Index: 422064 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5244. Min Act: -0.0003

Data Index: 584286 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5382. Min Act: -0.0003

Data Index: 128100 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5515. Min Act: -0.0003

Data Index: 293236 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.5725. Min Act: -0.0003

Data Index: 806402 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.7077. Min Range: -0.7077

Max Act: 0.4898. Min Act: -0.0003

Data Index: 458645 (C4 (Web Text))

Max Activating Token Index: 948