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

Dataset: The Pile

Neuron 1148 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.7698. Min Act: -0.0000

Data Index: 1033239 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.9248. Min Act: -0.0000

Data Index: 525327 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.4261. Min Act: -0.0000

Data Index: 901147 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.4888. Min Act: -0.0000

Data Index: 949867 (The Pile)

Max Activating Token Index: 839

Text #4

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.6175. Min Act: -0.0000

Data Index: 117301 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.5742. Min Act: -0.0000

Data Index: 1014677 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1002617 (The Pile)

Max Activating Token Index: 40

Text #7

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.4595. Min Act: -0.0000

Data Index: 1122018 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.6336. Min Act: -0.0000

Data Index: 688322 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.5343. Min Act: -0.0000

Data Index: 1995710 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.2831. Min Act: -0.0000

Data Index: 328894 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.5267. Min Act: -0.0000

Data Index: 387095 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1400286 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.3917. Min Act: -0.0000

Data Index: 1425699 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.3830. Min Act: -0.0000

Data Index: 855154 (The Pile)

Max Activating Token Index: 783

Text #15

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1671756 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.3712. Min Act: -0.0000

Data Index: 381880 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.3785. Min Act: 0.0000

Data Index: 1654234 (The Pile)

Max Activating Token Index: 846

Text #18

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.2986. Min Act: 0.0000

Data Index: 1845941 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 1.9248. Min Range: -1.9248

Max Act: 1.2866. Min Act: -0.0000

Data Index: 314848 (The Pile)

Max Activating Token Index: 623