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

Dataset: The Pile

Neuron 3091 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.9996. Min Act: -0.0000

Data Index: 615359 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7718. Min Act: -0.0000

Data Index: 500532 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7442. Min Act: -0.0000

Data Index: 853374 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6308. Min Act: -0.0000

Data Index: 310865 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.7225. Min Act: -0.0000

Data Index: 1985599 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.6114. Min Act: -0.0000

Data Index: 906955 (The Pile)

Max Activating Token Index: 165

Text #6

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.3722. Min Act: -0.0000

Data Index: 479371 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4838. Min Act: -0.0000

Data Index: 791679 (The Pile)

Max Activating Token Index: 870

Text #8

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4233. Min Act: -0.0000

Data Index: 494259 (The Pile)

Max Activating Token Index: 883

Text #9

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4617. Min Act: -0.0000

Data Index: 158653 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.3886. Min Act: -0.0000

Data Index: 311375 (The Pile)

Max Activating Token Index: 642

Text #11

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.3792. Min Act: -0.0000

Data Index: 1842524 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4125. Min Act: -0.0000

Data Index: 1332160 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.5189. Min Act: -0.0000

Data Index: 1667291 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4629. Min Act: -0.0000

Data Index: 705432 (The Pile)

Max Activating Token Index: 542

Text #15

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.3711. Min Act: -0.0000

Data Index: 1344861 (The Pile)

Max Activating Token Index: 655

Text #16

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.3883. Min Act: -0.0000

Data Index: 1900036 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4060. Min Act: -0.0000

Data Index: 1930288 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1032019 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 1.9996. Min Range: -1.9996

Max Act: 1.3491. Min Act: -0.0000

Data Index: 622963 (The Pile)

Max Activating Token Index: 467