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

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

Neuron 3206 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5833. Min Act: -0.0002

Data Index: 1026848 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5068. Min Act: -0.0002

Data Index: 735326 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.5579. Min Act: -0.0002

Data Index: 1080483 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4761. Min Act: -0.0002

Data Index: 52831 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4544. Min Act: -0.0001

Data Index: 1275392 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4594. Min Act: -0.0002

Data Index: 943240 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4323. Min Act: -0.0002

Data Index: 96330 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4151. Min Act: -0.0001

Data Index: 1057635 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3970. Min Act: -0.0002

Data Index: 607427 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3973. Min Act: -0.0001

Data Index: 1331223 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.4190. Min Act: -0.0001

Data Index: 792517 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3985. Min Act: -0.0002

Data Index: 132890 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3930. Min Act: -0.0002

Data Index: 63317 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3932. Min Act: -0.0002

Data Index: 360122 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3668. Min Act: -0.0001

Data Index: 155406 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3786. Min Act: -0.0002

Data Index: 291815 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1198144 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3291. Min Act: -0.0002

Data Index: 331411 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3773. Min Act: -0.0001

Data Index: 1290364 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.5833. Min Range: -0.5833

Max Act: 0.3619. Min Act: -0.0002

Data Index: 235081 (C4 (Web Text))

Max Activating Token Index: 560