Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 7 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.7540. Min Act: -0.0000

Data Index: 497496 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.7991. Min Act: -0.0000

Data Index: 396026 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.7699. Min Act: -0.0000

Data Index: 206500 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.6932. Min Act: -0.0000

Data Index: 1123667 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.7018. Min Act: -0.0000

Data Index: 1229875 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.5788. Min Act: -0.0000

Data Index: 984676 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.4714. Min Act: -0.0000

Data Index: 1197396 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.4720. Min Act: -0.0000

Data Index: 95961 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.4194. Min Act: -0.0000

Data Index: 277154 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.2923. Min Act: -0.0000

Data Index: 813882 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.4447. Min Act: -0.0000

Data Index: 724290 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.3751. Min Act: -0.0000

Data Index: 862845 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.4616. Min Act: -0.0000

Data Index: 578023 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.2351. Min Act: -0.0000

Data Index: 872246 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.2263. Min Act: -0.0000

Data Index: 294066 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.2549. Min Act: -0.0000

Data Index: 4163 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1258824 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1254191 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.3445. Min Act: -0.0000

Data Index: 505461 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 1.7991. Min Range: -1.7991

Max Act: 1.1363. Min Act: -0.0000

Data Index: 20999 (C4 (Web Text))

Max Activating Token Index: 490