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

Dataset: The Pile

Neuron 291 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2837. Min Range: -4.2837

Max Act: 4.2837. Min Act: -0.0000

Data Index: 612649 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 4.2837. Min Range: -4.2837

Max Act: 3.9258. Min Act: -0.0000

Data Index: 1036428 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 4.2837. Min Range: -4.2837

Max Act: 3.3912. Min Act: -0.0000

Data Index: 223573 (The Pile)

Max Activating Token Index: 936

Text #3

Max Range: 4.2837. Min Range: -4.2837

Max Act: 3.1805. Min Act: -0.0000

Data Index: 147936 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 4.2837. Min Range: -4.2837

Max Act: 3.0011. Min Act: -0.0000

Data Index: 1867549 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 4.2837. Min Range: -4.2837

Max Act: 3.2692. Min Act: -0.0000

Data Index: 1820797 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 4.2837. Min Range: -4.2837

Max Act: 3.0477. Min Act: -0.0000

Data Index: 1979692 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 4.2837. Min Range: -4.2837

Max Act: 3.0419. Min Act: -0.0000

Data Index: 1133067 (The Pile)

Max Activating Token Index: 912

Text #8

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.7754. Min Act: -0.0000

Data Index: 789936 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.6791. Min Act: -0.0000

Data Index: 960366 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.6349. Min Act: -0.0000

Data Index: 500922 (The Pile)

Max Activating Token Index: 51

Text #11

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.5122. Min Act: -0.0000

Data Index: 1876364 (The Pile)

Max Activating Token Index: 969

Text #12

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.6255. Min Act: -0.0000

Data Index: 311979 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.4573. Min Act: -0.0000

Data Index: 1479602 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.4632. Min Act: -0.0000

Data Index: 828596 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.4456. Min Act: -0.0000

Data Index: 1686778 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.4535. Min Act: -0.0000

Data Index: 1484016 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.2183. Min Act: -0.0000

Data Index: 1554518 (The Pile)

Max Activating Token Index: 865

Text #18

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.3678. Min Act: -0.0000

Data Index: 1525060 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 4.2837. Min Range: -4.2837

Max Act: 2.3727. Min Act: -0.0000

Data Index: 87150 (The Pile)

Max Activating Token Index: 438