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

Dataset: The Pile

Neuron 1247 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: 0.6037. Min Range: -0.6037

Max Act: 0.6037. Min Act: -0.0000

Data Index: 1469108 (The Pile)

Max Activating Token Index: 101

Text #1

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1817620 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1608086 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4127. Min Act: -0.0000

Data Index: 42650 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3867. Min Act: -0.0000

Data Index: 494905 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3869. Min Act: -0.0000

Data Index: 954467 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1021703 (The Pile)

Max Activating Token Index: 213

Text #7

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3857. Min Act: -0.0000

Data Index: 1884449 (The Pile)

Max Activating Token Index: 260

Text #8

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1259377 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1698718 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3634. Min Act: -0.0000

Data Index: 204751 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3479. Min Act: -0.0000

Data Index: 740525 (The Pile)

Max Activating Token Index: 185

Text #12

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3930. Min Act: -0.0000

Data Index: 627084 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3816. Min Act: -0.0000

Data Index: 341981 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3338. Min Act: -0.0000

Data Index: 17003 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1708000 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3647. Min Act: -0.0000

Data Index: 868173 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3427. Min Act: -0.0000

Data Index: 1548633 (The Pile)

Max Activating Token Index: 411

Text #18

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3489. Min Act: -0.0000

Data Index: 1712434 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.3611. Min Act: -0.0000

Data Index: 481665 (The Pile)

Max Activating Token Index: 816