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

Dataset: The Pile

Neuron 2139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5450. Min Act: -0.0000

Data Index: 382480 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5024. Min Act: -0.0000

Data Index: 417001 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5259. Min Act: -0.0000

Data Index: 390313 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4944. Min Act: -0.0000

Data Index: 872139 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1671333 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1134210 (The Pile)

Max Activating Token Index: 31

Text #6

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4555. Min Act: -0.0000

Data Index: 646947 (The Pile)

Max Activating Token Index: 707

Text #7

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1288301 (The Pile)

Max Activating Token Index: 92

Text #8

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.5108. Min Act: -0.0000

Data Index: 975466 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4558. Min Act: -0.0000

Data Index: 1766378 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4647. Min Act: -0.0000

Data Index: 820436 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1449427 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4702. Min Act: -0.0000

Data Index: 51650 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1775038 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1082457 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4686. Min Act: -0.0000

Data Index: 832435 (The Pile)

Max Activating Token Index: 102

Text #16

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4574. Min Act: -0.0000

Data Index: 681953 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4588. Min Act: -0.0000

Data Index: 155011 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1108760 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 0.5450. Min Range: -0.5450

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1140117 (The Pile)

Max Activating Token Index: 72