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

Dataset: The Pile

Neuron 4078 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1739747 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1908690 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1711334 (The Pile)

Max Activating Token Index: 602

Text #3

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1569 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6771. Min Act: -0.0000

Data Index: 931848 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6339. Min Act: -0.0000

Data Index: 603426 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1452440 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1872201 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.7286. Min Act: -0.0000

Data Index: 327008 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6367. Min Act: -0.0000

Data Index: 600408 (The Pile)

Max Activating Token Index: 841

Text #10

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1052773 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5610. Min Act: -0.0000

Data Index: 118374 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1609672 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5650. Min Act: -0.0000

Data Index: 1848367 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1662468 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5654. Min Act: -0.0000

Data Index: 458377 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1053238 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1355005 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1731617 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 0.8275. Min Range: -0.8275

Max Act: 0.5926. Min Act: -0.0000

Data Index: 835374 (The Pile)

Max Activating Token Index: 811