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

Dataset: The Pile

Neuron 445 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: 1.0922. Min Range: -1.0922

Max Act: 1.0922. Min Act: -0.0000

Data Index: 736141 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7774. Min Act: -0.0000

Data Index: 804381 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1391082 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7414. Min Act: -0.0000

Data Index: 1002895 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1336214 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1727495 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1247933 (The Pile)

Max Activating Token Index: 894

Text #7

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6943. Min Act: -0.0000

Data Index: 796623 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1654563 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1595256 (The Pile)

Max Activating Token Index: 136

Text #10

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6848. Min Act: -0.0000

Data Index: 360503 (The Pile)

Max Activating Token Index: 533

Text #11

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6089. Min Act: -0.0000

Data Index: 326942 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1631283 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6393. Min Act: -0.0000

Data Index: 95995 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6504. Min Act: -0.0000

Data Index: 74260 (The Pile)

Max Activating Token Index: 364

Text #15

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1505801 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1186471 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1961828 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1657183 (The Pile)

Max Activating Token Index: 70

Text #19

Max Range: 1.0922. Min Range: -1.0922

Max Act: 0.6021. Min Act: -0.0000

Data Index: 765587 (The Pile)

Max Activating Token Index: 347