Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3331 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.9966. Min Act: -0.0000

Data Index: 874329 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.9361. Min Act: -0.0000

Data Index: 45991 (The Pile)

Max Activating Token Index: 210

Text #2

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1590520 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8827. Min Act: -0.0000

Data Index: 368042 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.8457. Min Act: -0.0000

Data Index: 551076 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7882. Min Act: -0.0000

Data Index: 980372 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6855. Min Act: -0.0000

Data Index: 911174 (The Pile)

Max Activating Token Index: 1022

Text #7

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1537784 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7292. Min Act: -0.0000

Data Index: 761773 (The Pile)

Max Activating Token Index: 972

Text #9

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6891. Min Act: -0.0000

Data Index: 117671 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6927. Min Act: -0.0000

Data Index: 220493 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1285836 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1161967 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7013. Min Act: -0.0000

Data Index: 494446 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1625591 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6832. Min Act: -0.0000

Data Index: 626607 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.7184. Min Act: -0.0000

Data Index: 421273 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6318. Min Act: -0.0000

Data Index: 711858 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1477993 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.9966. Min Range: -0.9966

Max Act: 0.6291. Min Act: -0.0000

Data Index: 617216 (The Pile)

Max Activating Token Index: 1010