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

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

Neuron 4357 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: 0.1249. Min Range: -0.1249

Max Act: 0.1202. Min Act: -0.0001

Data Index: 549713 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1249. Min Act: -0.0001

Data Index: 877696 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1150. Min Act: -0.0001

Data Index: 919621 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1229. Min Act: -0.0001

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1057. Min Act: -0.0001

Data Index: 455438 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1032. Min Act: -0.0000

Data Index: 453766 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0972. Min Act: -0.0001

Data Index: 265472 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1233942 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1032. Min Act: -0.0001

Data Index: 111359 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0978. Min Act: -0.0000

Data Index: 111582 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0966. Min Act: -0.0001

Data Index: 312630 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1027. Min Act: -0.0001

Data Index: 47431 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0964. Min Act: -0.0001

Data Index: 575266 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0929. Min Act: -0.0001

Data Index: 447231 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1019681 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0966. Min Act: -0.0001

Data Index: 640966 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1598415 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1025. Min Act: -0.0001

Data Index: 682875 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1020. Min Act: -0.0000

Data Index: 1387432 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.0971. Min Act: -0.0001

Data Index: 465286 (C4 (Web Text))

Max Activating Token Index: 970