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

Dataset: The Pile

Neuron 273 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: 0.9242. Min Range: -0.9242

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1537210 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.9242. Min Act: -0.0000

Data Index: 688419 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1469940 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1621118 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7764. Min Act: -0.0000

Data Index: 116999 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1626225 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1457696 (The Pile)

Max Activating Token Index: 72

Text #7

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1907065 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1228128 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1198142 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1404794 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1656899 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7741. Min Act: -0.0000

Data Index: 1277035 (The Pile)

Max Activating Token Index: 145

Text #13

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6683. Min Act: -0.0000

Data Index: 870940 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7593. Min Act: -0.0000

Data Index: 931931 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7034. Min Act: -0.0000

Data Index: 147608 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7149. Min Act: -0.0000

Data Index: 630831 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1713560 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1962510 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.9242. Min Range: -0.9242

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1092449 (The Pile)

Max Activating Token Index: 32