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

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

Neuron 1974 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: 0.3828. Min Range: -0.3828

Max Act: 0.3828. Min Act: -0.0001

Data Index: 1027333 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3417. Min Act: -0.0001

Data Index: 201606 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1107851 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.3176. Min Act: -0.0001

Data Index: 508460 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2845. Min Act: -0.0001

Data Index: 219994 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2879. Min Act: -0.0001

Data Index: 993469 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2964. Min Act: -0.0001

Data Index: 826746 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2813. Min Act: -0.0001

Data Index: 192479 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2819. Min Act: -0.0001

Data Index: 159204 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2630. Min Act: -0.0001

Data Index: 418652 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2707. Min Act: -0.0001

Data Index: 724198 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2808. Min Act: -0.0001

Data Index: 936143 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2780. Min Act: -0.0001

Data Index: 675423 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2606. Min Act: -0.0001

Data Index: 252129 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2669. Min Act: -0.0001

Data Index: 626544 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2756. Min Act: -0.0001

Data Index: 1247508 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2655. Min Act: -0.0001

Data Index: 75020 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2773. Min Act: -0.0001

Data Index: 107841 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1334392 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.3828. Min Range: -0.3828

Max Act: 0.2712. Min Act: -0.0001

Data Index: 5173 (C4 (Web Text))

Max Activating Token Index: 389