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

Dataset: The Pile

Neuron 2223 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: 0.5381. Min Range: -0.5381

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1587375 (The Pile)

Max Activating Token Index: 325

Text #1

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4368. Min Act: -0.0000

Data Index: 1314942 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4319. Min Act: 0.0001

Data Index: 25086 (The Pile)

Max Activating Token Index: 4

Text #3

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1949400 (The Pile)

Max Activating Token Index: 432

Text #4

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4572. Min Act: -0.0000

Data Index: 16086 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4173. Min Act: -0.0000

Data Index: 725920 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3992. Min Act: -0.0000

Data Index: 235648 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3925. Min Act: -0.0000

Data Index: 475672 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1608655 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1083590 (The Pile)

Max Activating Token Index: 165

Text #10

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1704784 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1515801 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3620. Min Act: -0.0000

Data Index: 1022668 (The Pile)

Max Activating Token Index: 489

Text #13

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3742. Min Act: 0.0000

Data Index: 597784 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1607666 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3506. Min Act: -0.0000

Data Index: 712400 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3762. Min Act: -0.0000

Data Index: 757044 (The Pile)

Max Activating Token Index: 850

Text #17

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1574271 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3673. Min Act: -0.0000

Data Index: 1633411 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 0.5381. Min Range: -0.5381

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1331625 (The Pile)

Max Activating Token Index: 938