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

Dataset: The Pile

Neuron 288 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.5038. Min Act: -0.0000

Data Index: 1127706 (The Pile)

Max Activating Token Index: 667

Text #1

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.4027. Min Act: -0.0000

Data Index: 460758 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.3449. Min Act: -0.0000

Data Index: 1787708 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1720249 (The Pile)

Max Activating Token Index: 829

Text #4

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2574. Min Act: -0.0000

Data Index: 751238 (The Pile)

Max Activating Token Index: 807

Text #5

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2884. Min Act: -0.0000

Data Index: 1130784 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1676. Min Act: -0.0000

Data Index: 452260 (The Pile)

Max Activating Token Index: 855

Text #7

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2688. Min Act: -0.0000

Data Index: 478706 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2602. Min Act: -0.0000

Data Index: 1086662 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1982. Min Act: -0.0000

Data Index: 1915814 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2300. Min Act: -0.0000

Data Index: 1421410 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2337. Min Act: -0.0000

Data Index: 1016024 (The Pile)

Max Activating Token Index: 949

Text #12

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1387. Min Act: -0.0000

Data Index: 867333 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1146891 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1943873 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2200. Min Act: -0.0000

Data Index: 965382 (The Pile)

Max Activating Token Index: 801

Text #16

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.2389. Min Act: -0.0000

Data Index: 603147 (The Pile)

Max Activating Token Index: 659

Text #17

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1989. Min Act: -0.0000

Data Index: 1720349 (The Pile)

Max Activating Token Index: 303

Text #18

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1828629 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 1.5038. Min Range: -1.5038

Max Act: 1.1937. Min Act: -0.0000

Data Index: 145671 (The Pile)

Max Activating Token Index: 808