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

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

Neuron 3723 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.8397. Min Act: -0.0002

Data Index: 442542 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.8397. Min Act: -0.0002

Data Index: 1346965 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.7847. Min Act: -0.0002

Data Index: 1265859 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6910. Min Act: -0.0002

Data Index: 493374 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.7819. Min Act: -0.0002

Data Index: 597788 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.7049. Min Act: -0.0002

Data Index: 758595 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6607. Min Act: -0.0002

Data Index: 67075 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.7083. Min Act: -0.0002

Data Index: 189969 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6546. Min Act: -0.0002

Data Index: 129198 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.7194. Min Act: -0.0002

Data Index: 309200 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6862. Min Act: -0.0002

Data Index: 898818 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6860. Min Act: -0.0002

Data Index: 1025843 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6584. Min Act: -0.0002

Data Index: 671654 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6831. Min Act: -0.0002

Data Index: 1323945 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6353. Min Act: -0.0002

Data Index: 983 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6988. Min Act: -0.0002

Data Index: 285383 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6776. Min Act: -0.0002

Data Index: 407398 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6766. Min Act: -0.0002

Data Index: 763990 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6508. Min Act: -0.0002

Data Index: 416468 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5892. Min Act: -0.0002

Data Index: 1292459 (C4 (Web Text))

Max Activating Token Index: 155