Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 129 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.8036. Min Act: -0.0000

Data Index: 981156 (The Pile)

Max Activating Token Index: 723

Text #1

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1079230 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.7110. Min Act: -0.0001

Data Index: 234252 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6886. Min Act: -0.0000

Data Index: 249890 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6813. Min Act: -0.0000

Data Index: 506765 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6669. Min Act: -0.0001

Data Index: 734145 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1635292 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6265. Min Act: -0.0000

Data Index: 116168 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1602165 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1841404 (The Pile)

Max Activating Token Index: 223

Text #10

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6340. Min Act: -0.0000

Data Index: 984149 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1003444 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1369209 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1981637 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6046. Min Act: -0.0001

Data Index: 1971218 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1593182 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1102632 (The Pile)

Max Activating Token Index: 441

Text #17

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5587. Min Act: -0.0000

Data Index: 836226 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5920. Min Act: -0.0000

Data Index: 1393383 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5896. Min Act: -0.0000

Data Index: 543918 (The Pile)

Max Activating Token Index: 551