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

Dataset: The Pile

Neuron 4875 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1304625 (The Pile)

Max Activating Token Index: 614

Text #1

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4698. Min Act: -0.0000

Data Index: 9466 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4459. Min Act: -0.0000

Data Index: 110599 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3879. Min Act: -0.0000

Data Index: 547831 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4328. Min Act: -0.0000

Data Index: 942870 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3726. Min Act: -0.0000

Data Index: 25532 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1438024 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3917. Min Act: -0.0000

Data Index: 151351 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3769. Min Act: -0.0000

Data Index: 557087 (The Pile)

Max Activating Token Index: 65

Text #9

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1928207 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1994086 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1554506 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1778946 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1098444 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3471. Min Act: -0.0000

Data Index: 148835 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3527. Min Act: -0.0000

Data Index: 853503 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3521. Min Act: -0.0000

Data Index: 431522 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1793392 (The Pile)

Max Activating Token Index: 43

Text #18

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3397. Min Act: -0.0000

Data Index: 1198870 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1987261 (The Pile)

Max Activating Token Index: 900