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

Dataset: The Pile

Neuron 3891 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: 0.5974. Min Range: -0.5974

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1038311 (The Pile)

Max Activating Token Index: 680

Text #1

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.5457. Min Act: -0.0000

Data Index: 474537 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1107389 (The Pile)

Max Activating Token Index: 269

Text #3

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1424377 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1248296 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4549. Min Act: -0.0000

Data Index: 674927 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1988275 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1715447 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3894. Min Act: -0.0000

Data Index: 76465 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1758520 (The Pile)

Max Activating Token Index: 845

Text #10

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1361606 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4261. Min Act: -0.0000

Data Index: 69734 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3788. Min Act: -0.0000

Data Index: 688028 (The Pile)

Max Activating Token Index: 325

Text #13

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1809328 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.4034. Min Act: -0.0000

Data Index: 247393 (The Pile)

Max Activating Token Index: 493

Text #15

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3861. Min Act: -0.0000

Data Index: 612630 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1560946 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3792. Min Act: -0.0000

Data Index: 1813000 (The Pile)

Max Activating Token Index: 725

Text #18

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3740. Min Act: -0.0000

Data Index: 952878 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.5974. Min Range: -0.5974

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1156832 (The Pile)

Max Activating Token Index: 854