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

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

Neuron 2768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5404. Min Range: -2.5404

Max Act: 2.5404. Min Act: -0.0000

Data Index: 766023 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 2.5404. Min Range: -2.5404

Max Act: 2.4742. Min Act: -0.0000

Data Index: 1202034 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 2.5404. Min Range: -2.5404

Max Act: 2.2507. Min Act: -0.0000

Data Index: 694433 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 2.5404. Min Range: -2.5404

Max Act: 2.0097. Min Act: -0.0000

Data Index: 1018622 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.7692. Min Act: -0.0000

Data Index: 257289 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.7130. Min Act: -0.0000

Data Index: 740611 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.7277. Min Act: -0.0000

Data Index: 715736 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.6823. Min Act: -0.0000

Data Index: 11391 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.7471. Min Act: -0.0000

Data Index: 895233 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.7241. Min Act: -0.0000

Data Index: 932697 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.5913. Min Act: -0.0000

Data Index: 450751 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.6886. Min Act: -0.0000

Data Index: 61406 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.6037. Min Act: -0.0000

Data Index: 986462 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.6266. Min Act: -0.0000

Data Index: 897127 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.7138. Min Act: -0.0000

Data Index: 89663 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.6012. Min Act: -0.0000

Data Index: 1300499 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.6500. Min Act: -0.0000

Data Index: 1092370 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.6422. Min Act: -0.0000

Data Index: 641981 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.5311. Min Act: -0.0000

Data Index: 138425 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 2.5404. Min Range: -2.5404

Max Act: 1.4487. Min Act: -0.0000

Data Index: 475298 (C4 (Web Text))

Max Activating Token Index: 994