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

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

Neuron 3115 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: 0.0037. Min Range: -0.0037

Max Act: 0.0037. Min Act: -0.0002

Data Index: 1435518 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1498819 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0036. Min Act: -0.0003

Data Index: 881020 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0036. Min Act: -0.0002

Data Index: 1614061 (Python Code)

Max Activating Token Index: 877

Text #4

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0036. Min Act: -0.0003

Data Index: 464562 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1196184 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 299045 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 398777 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 547961 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 435260 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 878393 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1600478 (Python Code)

Max Activating Token Index: 1019

Text #12

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 51572 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0002

Data Index: 982273 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 662471 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1196 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 51305 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1522223 (Python Code)

Max Activating Token Index: 453

Text #18

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 332648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 504266 (C4 (Web Text))

Max Activating Token Index: 476