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

Dataset: The Pile

Neuron 2082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.5210. Min Act: -0.0000

Data Index: 484796 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4595. Min Act: -0.0000

Data Index: 65326 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4561. Min Act: -0.0000

Data Index: 481748 (The Pile)

Max Activating Token Index: 403

Text #3

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1964494 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1173796 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4234. Min Act: -0.0000

Data Index: 636407 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1270766 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4218. Min Act: -0.0000

Data Index: 240205 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4247. Min Act: -0.0000

Data Index: 717345 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1594868 (The Pile)

Max Activating Token Index: 177

Text #10

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4182. Min Act: -0.0000

Data Index: 356053 (The Pile)

Max Activating Token Index: 98

Text #11

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4335. Min Act: -0.0001

Data Index: 99726 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1527725 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3819. Min Act: -0.0000

Data Index: 800350 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1843937 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1734993 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1192358 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.4113. Min Act: -0.0001

Data Index: 1029587 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3886. Min Act: -0.0000

Data Index: 892935 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.3682. Min Act: -0.0000

Data Index: 754079 (The Pile)

Max Activating Token Index: 770