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

Dataset: The Pile

Neuron 2516 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: 4.6909. Min Range: -4.6909

Max Act: 4.6909. Min Act: -0.0000

Data Index: 605009 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.1478. Min Act: -0.0000

Data Index: 1999174 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.2548. Min Act: -0.0000

Data Index: 939267 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.3691. Min Act: -0.0000

Data Index: 1606090 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.9882. Min Act: -0.0000

Data Index: 746148 (The Pile)

Max Activating Token Index: 58

Text #5

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.2288. Min Act: -0.0000

Data Index: 1332263 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.4967. Min Act: -0.0000

Data Index: 1829281 (The Pile)

Max Activating Token Index: 516

Text #7

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.0004. Min Act: -0.0000

Data Index: 1123492 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.1455. Min Act: -0.0000

Data Index: 430699 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.9819. Min Act: -0.0000

Data Index: 1587746 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.8025. Min Act: -0.0000

Data Index: 1397299 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.9530. Min Act: -0.0000

Data Index: 129431 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.5041. Min Act: -0.0000

Data Index: 1890177 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.8510. Min Act: -0.0000

Data Index: 1958894 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 4.6909. Min Range: -4.6909

Max Act: 2.9038. Min Act: -0.0000

Data Index: 1380385 (The Pile)

Max Activating Token Index: 640

Text #15

Max Range: 4.6909. Min Range: -4.6909

Max Act: 4.0177. Min Act: -0.0000

Data Index: 1964497 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.8464. Min Act: -0.0000

Data Index: 1319516 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.4630. Min Act: -0.0000

Data Index: 699140 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.7920. Min Act: -0.0000

Data Index: 502717 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 4.6909. Min Range: -4.6909

Max Act: 3.9712. Min Act: -0.0000

Data Index: 27037 (The Pile)

Max Activating Token Index: 70