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

Dataset: The Pile

Neuron 3878 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: 1.0049. Min Range: -1.0049

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1967630 (The Pile)

Max Activating Token Index: 417

Text #1

Max Range: 1.0049. Min Range: -1.0049

Max Act: 1.0047. Min Act: -0.0000

Data Index: 984835 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.9814. Min Act: -0.0000

Data Index: 208255 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1130910 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1802928 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8800. Min Act: -0.0000

Data Index: 105609 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8645. Min Act: -0.0001

Data Index: 1996916 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.9398. Min Act: -0.0000

Data Index: 41818 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1451815 (The Pile)

Max Activating Token Index: 695

Text #9

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1537715 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8609. Min Act: -0.0000

Data Index: 563300 (The Pile)

Max Activating Token Index: 335

Text #11

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1336534 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1368518 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.7204. Min Act: -0.0000

Data Index: 360721 (The Pile)

Max Activating Token Index: 340

Text #14

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1807079 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1961524 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8331. Min Act: -0.0000

Data Index: 458308 (The Pile)

Max Activating Token Index: 487

Text #17

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1366729 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1664708 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 1.0049. Min Range: -1.0049

Max Act: 0.7916. Min Act: -0.0000

Data Index: 102832 (The Pile)

Max Activating Token Index: 282