Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3304 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.9955. Min Act: -0.0000

Data Index: 1668304 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.9225. Min Act: -0.0000

Data Index: 685604 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8048. Min Act: -0.0000

Data Index: 1096423 (The Pile)

Max Activating Token Index: 612

Text #3

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7497. Min Act: -0.0000

Data Index: 902859 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7006. Min Act: -0.0000

Data Index: 1640226 (The Pile)

Max Activating Token Index: 390

Text #5

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.8351. Min Act: -0.0000

Data Index: 1210141 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7703. Min Act: -0.0000

Data Index: 981670 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6379. Min Act: -0.0000

Data Index: 1389601 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7105. Min Act: -0.0000

Data Index: 868773 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1192377 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.7257. Min Act: -0.0000

Data Index: 532148 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5715. Min Act: -0.0000

Data Index: 1928666 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5365. Min Act: -0.0000

Data Index: 158202 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6729. Min Act: -0.0000

Data Index: 1508947 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5717. Min Act: -0.0000

Data Index: 593906 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.6106. Min Act: -0.0000

Data Index: 997623 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5503. Min Act: -0.0000

Data Index: 1067764 (The Pile)

Max Activating Token Index: 729

Text #17

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1214498 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.4253. Min Act: -0.0000

Data Index: 1630644 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 1.9955. Min Range: -1.9955

Max Act: 1.5611. Min Act: -0.0000

Data Index: 723420 (The Pile)

Max Activating Token Index: 443