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

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

Neuron 1862 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2983. Min Range: -2.2983

Max Act: 2.2983. Min Act: -0.0000

Data Index: 984533 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.8526. Min Act: -0.0000

Data Index: 493136 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 2.2983. Min Range: -2.2983

Max Act: 2.0476. Min Act: -0.0000

Data Index: 362721 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.8915. Min Act: -0.0000

Data Index: 641782 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.8700. Min Act: -0.0000

Data Index: 101885 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.6231. Min Act: -0.0000

Data Index: 1153014 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.6693. Min Act: -0.0000

Data Index: 1122556 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.6434. Min Act: -0.0000

Data Index: 1211366 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.4457. Min Act: -0.0000

Data Index: 928330 (C4 (Web Text))

Max Activating Token Index: 371

Text #9

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1295285 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.6242. Min Act: -0.0000

Data Index: 197657 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.6002. Min Act: -0.0000

Data Index: 867108 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.6614. Min Act: -0.0000

Data Index: 967341 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.5215. Min Act: -0.0000

Data Index: 328665 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.5511. Min Act: -0.0000

Data Index: 187255 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.4524. Min Act: -0.0000

Data Index: 854525 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1174172 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.4822. Min Act: -0.0000

Data Index: 733450 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.4810. Min Act: -0.0000

Data Index: 386770 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 2.2983. Min Range: -2.2983

Max Act: 1.4342. Min Act: -0.0000

Data Index: 833891 (C4 (Web Text))

Max Activating Token Index: 124