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

Dataset: The Pile

Neuron 992 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.6950. Min Act: -0.0000

Data Index: 556327 (The Pile)

Max Activating Token Index: 397

Text #1

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.3441. Min Act: -0.0000

Data Index: 709493 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1039066 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1882215 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.3794. Min Act: -0.0000

Data Index: 552365 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.2282. Min Act: -0.0000

Data Index: 350540 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.1934. Min Act: -0.0000

Data Index: 1617682 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.2161. Min Act: -0.0000

Data Index: 1222386 (The Pile)

Max Activating Token Index: 184

Text #8

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.1739. Min Act: -0.0000

Data Index: 912201 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1044182 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.1113. Min Act: -0.0000

Data Index: 1456510 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.1392. Min Act: -0.0000

Data Index: 125684 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1311965 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0432. Min Act: -0.0000

Data Index: 780854 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1485466 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0675. Min Act: -0.0000

Data Index: 298448 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0252. Min Act: -0.0000

Data Index: 1559316 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0252. Min Act: -0.0000

Data Index: 986556 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.1022. Min Act: -0.0000

Data Index: 673092 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 1.6950. Min Range: -1.6950

Max Act: 1.0067. Min Act: -0.0000

Data Index: 1478598 (The Pile)

Max Activating Token Index: 452