Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1937 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1531. Min Act: -0.0002

Data Index: 1062736 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1284874 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1302. Min Act: -0.0002

Data Index: 739220 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1036. Min Act: -0.0000

Data Index: 722068 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0999. Min Act: -0.0002

Data Index: 787893 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1013. Min Act: -0.0002

Data Index: 144529 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0999. Min Act: -0.0002

Data Index: 181726 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.1030. Min Act: -0.0002

Data Index: 405321 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0999. Min Act: -0.0002

Data Index: 167799 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0966. Min Act: -0.0001

Data Index: 679950 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0961. Min Act: -0.0002

Data Index: 804171 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0949. Min Act: -0.0002

Data Index: 247397 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1137944 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1355728 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0899. Min Act: -0.0002

Data Index: 996736 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0897. Min Act: -0.0002

Data Index: 400945 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0873. Min Act: -0.0002

Data Index: 173861 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0873. Min Act: -0.0002

Data Index: 202432 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0871. Min Act: -0.0002

Data Index: 441126 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.1531. Min Range: -0.1531

Max Act: 0.0888. Min Act: -0.0002

Data Index: 527075 (C4 (Web Text))

Max Activating Token Index: 277