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

Dataset: The Pile

Neuron 3010 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.6588. Min Act: -0.0000

Data Index: 1387258 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2706. Min Act: -0.0000

Data Index: 785108 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.4638. Min Act: -0.0000

Data Index: 1444809 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.4381. Min Act: -0.0000

Data Index: 361772 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3152. Min Act: -0.0000

Data Index: 778188 (The Pile)

Max Activating Token Index: 384

Text #5

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3211. Min Act: -0.0000

Data Index: 386728 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1419378 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1506669 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.1841. Min Act: -0.0000

Data Index: 191801 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2965. Min Act: -0.0000

Data Index: 288224 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.0350. Min Act: -0.0000

Data Index: 584649 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1275509 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1367320 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.1643. Min Act: -0.0000

Data Index: 67988 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2812. Min Act: -0.0000

Data Index: 842884 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2824. Min Act: -0.0000

Data Index: 1967814 (The Pile)

Max Activating Token Index: 209

Text #16

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.2992. Min Act: -0.0000

Data Index: 889541 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1436338 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1768965 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 1.6588. Min Range: -1.6588

Max Act: 1.0763. Min Act: -0.0000

Data Index: 388062 (The Pile)

Max Activating Token Index: 527