Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1940 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1661933 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5444. Min Act: -0.0000

Data Index: 66880 (The Pile)

Max Activating Token Index: 32

Text #2

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1861064 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4577. Min Act: -0.0000

Data Index: 566962 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4469. Min Act: -0.0000

Data Index: 754687 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1026572 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4024. Min Act: -0.0000

Data Index: 316151 (The Pile)

Max Activating Token Index: 966

Text #7

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3865. Min Act: -0.0000

Data Index: 1403440 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3416. Min Act: -0.0000

Data Index: 188582 (The Pile)

Max Activating Token Index: 875

Text #9

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3707. Min Act: -0.0000

Data Index: 684318 (The Pile)

Max Activating Token Index: 881

Text #10

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3531. Min Act: -0.0000

Data Index: 8551 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3598. Min Act: -0.0000

Data Index: 140965 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3266. Min Act: -0.0000

Data Index: 194228 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3187. Min Act: -0.0000

Data Index: 928051 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3397. Min Act: -0.0000

Data Index: 265710 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3305. Min Act: -0.0000

Data Index: 567601 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3360. Min Act: -0.0000

Data Index: 195533 (The Pile)

Max Activating Token Index: 811

Text #17

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1874147 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3267. Min Act: -0.0000

Data Index: 593867 (The Pile)

Max Activating Token Index: 624

Text #19

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3354. Min Act: -0.0000

Data Index: 979414 (The Pile)

Max Activating Token Index: 303