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

Dataset: The Pile

Neuron 2575 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: 5.5406. Min Range: -5.5406

Max Act: 5.5406. Min Act: -0.0000

Data Index: 246374 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 5.5406. Min Range: -5.5406

Max Act: 5.4941. Min Act: -0.0000

Data Index: 46439 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 5.5406. Min Range: -5.5406

Max Act: 5.2332. Min Act: -0.0000

Data Index: 673125 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 5.5406. Min Range: -5.5406

Max Act: 5.2855. Min Act: -0.0000

Data Index: 265749 (The Pile)

Max Activating Token Index: 690

Text #4

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.6185. Min Act: -0.0000

Data Index: 910892 (The Pile)

Max Activating Token Index: 741

Text #5

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.4173. Min Act: -0.0000

Data Index: 556908 (The Pile)

Max Activating Token Index: 963

Text #6

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.7911. Min Act: -0.0000

Data Index: 53833 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.6280. Min Act: -0.0000

Data Index: 1418909 (The Pile)

Max Activating Token Index: 6

Text #8

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.3645. Min Act: -0.0000

Data Index: 242919 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.0769. Min Act: -0.0000

Data Index: 1192487 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.0713. Min Act: -0.0000

Data Index: 104512 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.2715. Min Act: -0.0000

Data Index: 800599 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.2393. Min Act: -0.0000

Data Index: 874116 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.2347. Min Act: -0.0000

Data Index: 809960 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.1996. Min Act: -0.0000

Data Index: 985500 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.0142. Min Act: -0.0000

Data Index: 1146625 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.2416. Min Act: -0.0000

Data Index: 1124364 (The Pile)

Max Activating Token Index: 114

Text #17

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.2530. Min Act: -0.0000

Data Index: 974537 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 5.5406. Min Range: -5.5406

Max Act: 3.8959. Min Act: -0.0000

Data Index: 367794 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 5.5406. Min Range: -5.5406

Max Act: 4.0049. Min Act: -0.0000

Data Index: 1502229 (The Pile)

Max Activating Token Index: 741