Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3884 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.6274. Min Act: -0.0001

Data Index: 1315457 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.4782. Min Act: -0.0001

Data Index: 537292 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.3816. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.3574. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1985. Min Act: -0.0001

Data Index: 46696 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1830. Min Act: -0.0001

Data Index: 442873 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0580. Min Act: -0.0001

Data Index: 58407 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1468. Min Act: -0.0001

Data Index: 336087 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0777. Min Act: -0.0001

Data Index: 449826 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0613. Min Act: -0.0001

Data Index: 954086 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1227. Min Act: -0.0001

Data Index: 1216219 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0597. Min Act: -0.0001

Data Index: 64293 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 1.6274. Min Range: -1.6274

Max Act: 0.9913. Min Act: -0.0001

Data Index: 202566 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1401061 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1288. Min Act: -0.0001

Data Index: 981776 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.1269. Min Act: -0.0001

Data Index: 1034479 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0714. Min Act: -0.0001

Data Index: 162973 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0230. Min Act: -0.0001

Data Index: 1198238 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.6274. Min Range: -1.6274

Max Act: 1.0874. Min Act: -0.0001

Data Index: 82839 (C4 (Web Text))

Max Activating Token Index: 279