Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3933. Min Act: -0.0000

Data Index: 556729 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1995528 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3372. Min Act: -0.0000

Data Index: 1192540 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1517427 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2052. Min Act: -0.0000

Data Index: 276763 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2329. Min Act: -0.0000

Data Index: 1626663 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2599. Min Act: -0.0000

Data Index: 1525172 (The Pile)

Max Activating Token Index: 788

Text #7

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2561. Min Act: -0.0000

Data Index: 69368 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1485. Min Act: -0.0000

Data Index: 210176 (The Pile)

Max Activating Token Index: 311

Text #9

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1193686 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.2082. Min Act: -0.0000

Data Index: 1396248 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1259899 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1982. Min Act: -0.0000

Data Index: 247340 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1725. Min Act: -0.0000

Data Index: 413272 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1511. Min Act: -0.0000

Data Index: 534592 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.0487. Min Act: -0.0000

Data Index: 840775 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1009616 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1041. Min Act: -0.0000

Data Index: 588369 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1767411 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 1.3966. Min Range: -1.3966

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1895737 (The Pile)

Max Activating Token Index: 33