Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 742 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.6600. Min Act: -0.0000

Data Index: 1341798 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.5009. Min Act: -0.0000

Data Index: 814943 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.5267. Min Act: -0.0000

Data Index: 865983 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4330. Min Act: -0.0000

Data Index: 404915 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.2813. Min Act: -0.0000

Data Index: 1784776 (The Pile)

Max Activating Token Index: 962

Text #5

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.5191. Min Act: -0.0000

Data Index: 828115 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4136. Min Act: -0.0000

Data Index: 584346 (The Pile)

Max Activating Token Index: 55

Text #7

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.4764. Min Act: -0.0000

Data Index: 730355 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3875. Min Act: -0.0000

Data Index: 114735 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1129862 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.2820. Min Act: -0.0000

Data Index: 1024418 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3408. Min Act: -0.0000

Data Index: 351068 (The Pile)

Max Activating Token Index: 674

Text #12

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3486. Min Act: -0.0000

Data Index: 1322757 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.2586. Min Act: -0.0000

Data Index: 1805514 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.2638. Min Act: -0.0000

Data Index: 785980 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1509461 (The Pile)

Max Activating Token Index: 75

Text #16

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1337532 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.2442. Min Act: -0.0000

Data Index: 347295 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3895. Min Act: -0.0000

Data Index: 627264 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 1.6600. Min Range: -1.6600

Max Act: 1.3050. Min Act: -0.0000

Data Index: 628925 (The Pile)

Max Activating Token Index: 251