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

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

Neuron 3933 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.2871. Min Act: -0.0000

Data Index: 111969 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.2742. Min Act: -0.0000

Data Index: 726011 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.2152. Min Act: -0.0000

Data Index: 213165 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.2136. Min Act: -0.0000

Data Index: 598526 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1993. Min Act: -0.0000

Data Index: 969510 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1116212 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1146. Min Act: -0.0000

Data Index: 878880 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1135. Min Act: -0.0000

Data Index: 721197 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1780. Min Act: -0.0000

Data Index: 838091 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1296767 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1640. Min Act: -0.0000

Data Index: 645192 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1518. Min Act: -0.0000

Data Index: 118902 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1477. Min Act: -0.0000

Data Index: 101795 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1128. Min Act: -0.0000

Data Index: 337791 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1820. Min Act: -0.0000

Data Index: 520140 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1308622 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1310582 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.0796. Min Act: -0.0000

Data Index: 22209 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.2871. Min Range: -1.2871

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1120688 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 1.2871. Min Range: -1.2871

Max Act: 0.9844. Min Act: -0.0000

Data Index: 603882 (C4 (Web Text))

Max Activating Token Index: 11