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

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

Neuron 2455 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.9780. Min Act: -0.0000

Data Index: 797456 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.9646. Min Act: -0.0000

Data Index: 619265 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.6125. Min Act: -0.0000

Data Index: 250327 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.5592. Min Act: -0.0000

Data Index: 574167 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.8903. Min Act: -0.0000

Data Index: 122258 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.0750. Min Act: -0.0001

Data Index: 38951 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.7777. Min Act: -0.0001

Data Index: 9678 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.6804. Min Act: -0.0000

Data Index: 80770 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.5183. Min Act: -0.0000

Data Index: 1065643 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.3343. Min Act: -0.0000

Data Index: 708123 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.2173. Min Act: -0.0000

Data Index: 1227980 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.6005. Min Act: -0.0000

Data Index: 622864 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.3766. Min Act: -0.0000

Data Index: 954434 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.3784. Min Act: -0.0000

Data Index: 855652 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.3356. Min Act: -0.0000

Data Index: 1217314 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 4.9780. Min Range: -4.9780

Max Act: 3.7987. Min Act: -0.0000

Data Index: 237065 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.3854. Min Act: -0.0001

Data Index: 239353 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.3355. Min Act: -0.0001

Data Index: 1032415 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.3327. Min Act: -0.0000

Data Index: 355877 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 4.9780. Min Range: -4.9780

Max Act: 4.1055. Min Act: -0.0001

Data Index: 697989 (C4 (Web Text))

Max Activating Token Index: 727