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

Dataset: The Pile

Neuron 2738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.3012. Min Act: -0.0000

Data Index: 746758 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2682. Min Act: -0.0000

Data Index: 867046 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2669. Min Act: -0.0000

Data Index: 1081518 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1321783 (The Pile)

Max Activating Token Index: 157

Text #4

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2523. Min Act: -0.0000

Data Index: 251308 (The Pile)

Max Activating Token Index: 502

Text #5

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1982368 (The Pile)

Max Activating Token Index: 373

Text #6

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2470. Min Act: -0.0000

Data Index: 18850 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2519. Min Act: -0.0000

Data Index: 1708678 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2450. Min Act: -0.0000

Data Index: 1309879 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1363425 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2313. Min Act: -0.0000

Data Index: 523267 (The Pile)

Max Activating Token Index: 206

Text #11

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2321. Min Act: -0.0000

Data Index: 290744 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1138425 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1574170 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2311. Min Act: -0.0000

Data Index: 599203 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1012519 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2421. Min Act: -0.0000

Data Index: 1289175 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2034. Min Act: -0.0000

Data Index: 674489 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2113. Min Act: -0.0000

Data Index: 77196 (The Pile)

Max Activating Token Index: 698

Text #19

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2214. Min Act: -0.0000

Data Index: 802200 (The Pile)

Max Activating Token Index: 395