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

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

Neuron 4527 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.9742. Min Act: -0.0000

Data Index: 827699 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.9328. Min Act: -0.0000

Data Index: 537584 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.6422. Min Act: -0.0001

Data Index: 840575 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.4226. Min Act: -0.0000

Data Index: 1221542 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.2497. Min Act: -0.0000

Data Index: 364128 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.1388. Min Act: -0.0000

Data Index: 423892 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.2572. Min Act: -0.0000

Data Index: 64645 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.3551. Min Act: -0.0000

Data Index: 410624 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.2174. Min Act: -0.0000

Data Index: 730717 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.0978. Min Act: -0.0000

Data Index: 1353363 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.3326. Min Act: -0.0000

Data Index: 795605 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.1973. Min Act: -0.0000

Data Index: 22443 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.0637. Min Act: -0.0000

Data Index: 858858 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.5667. Min Act: -0.0000

Data Index: 893586 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.0439. Min Act: -0.0000

Data Index: 622187 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.0306. Min Act: -0.0000

Data Index: 1284984 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.0033. Min Act: -0.0000

Data Index: 751824 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 2.9742. Min Range: -2.9742

Max Act: 1.8879. Min Act: -0.0000

Data Index: 523801 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.1017. Min Act: -0.0000

Data Index: 842617 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 2.9742. Min Range: -2.9742

Max Act: 2.1157. Min Act: -0.0000

Data Index: 734258 (C4 (Web Text))

Max Activating Token Index: 95