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

Dataset: The Pile

Neuron 677 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: 1.6927. Min Range: -1.6927

Max Act: 1.6927. Min Act: -0.0000

Data Index: 1742636 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.1508. Min Act: -0.0000

Data Index: 546717 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.1327. Min Act: -0.0000

Data Index: 753536 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8660. Min Act: -0.0000

Data Index: 359818 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1150125 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1805749 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8719. Min Act: -0.0000

Data Index: 117379 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8912. Min Act: -0.0000

Data Index: 361773 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1021144 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1959517 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1877031 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1741041 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1369058 (The Pile)

Max Activating Token Index: 320

Text #13

Max Range: 1.6927. Min Range: -1.6927

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1341205 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8871. Min Act: -0.0000

Data Index: 768309 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1915357 (The Pile)

Max Activating Token Index: 208

Text #16

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.7549. Min Act: -0.0000

Data Index: 285409 (The Pile)

Max Activating Token Index: 949

Text #17

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8043. Min Act: -0.0000

Data Index: 134614 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8395. Min Act: -0.0000

Data Index: 398375 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 1.6927. Min Range: -1.6927

Max Act: 0.8076. Min Act: -0.0000

Data Index: 687273 (The Pile)

Max Activating Token Index: 911