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

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

Neuron 3637 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1355. Min Act: -0.0000

Data Index: 12673 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1428021 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1552733 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1066. Min Act: -0.0000

Data Index: 974309 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0965. Min Act: -0.0000

Data Index: 899169 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1348054 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1649065 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.1049. Min Act: -0.0000

Data Index: 134675 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1655078 (Python Code)

Max Activating Token Index: 570

Text #9

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1170184 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1463592 (Python Code)

Max Activating Token Index: 714

Text #11

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0809. Min Act: -0.0000

Data Index: 672832 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0878. Min Act: -0.0000

Data Index: 312771 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0838. Min Act: -0.0000

Data Index: 875881 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0876. Min Act: -0.0000

Data Index: 459267 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1241640 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0786. Min Act: -0.0000

Data Index: 785712 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0844. Min Act: -0.0000

Data Index: 863310 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0803. Min Act: -0.0000

Data Index: 987854 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.1355. Min Range: -0.1355

Max Act: 0.0822. Min Act: -0.0000

Data Index: 645417 (C4 (Web Text))

Max Activating Token Index: 925