Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2642 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6816. Min Act: -0.0001

Data Index: 453087 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6567. Min Act: -0.0002

Data Index: 795196 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6528. Min Act: -0.0002

Data Index: 837698 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5855. Min Act: -0.0002

Data Index: 1305874 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1273774 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6007. Min Act: -0.0001

Data Index: 1049023 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5353. Min Act: -0.0001

Data Index: 402475 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5398. Min Act: -0.0001

Data Index: 764775 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5188. Min Act: -0.0001

Data Index: 429037 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5290. Min Act: -0.0001

Data Index: 1202874 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5475. Min Act: -0.0001

Data Index: 1272733 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5293. Min Act: -0.0001

Data Index: 497508 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6040. Min Act: -0.0001

Data Index: 72856 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5169. Min Act: -0.0001

Data Index: 1160020 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5249. Min Act: -0.0001

Data Index: 972974 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5795. Min Act: -0.0001

Data Index: 186129 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4827. Min Act: -0.0001

Data Index: 332505 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5560. Min Act: -0.0001

Data Index: 521788 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1120623 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5359. Min Act: -0.0002

Data Index: 232842 (C4 (Web Text))

Max Activating Token Index: 734