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

Dataset: The Pile

Neuron 3382 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: 5.1861. Min Range: -5.1861

Max Act: 5.1861. Min Act: -0.0000

Data Index: 877146 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.5007. Min Act: -0.0000

Data Index: 408852 (The Pile)

Max Activating Token Index: 46

Text #2

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.1761. Min Act: -0.0000

Data Index: 1384343 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.1884. Min Act: -0.0000

Data Index: 426550 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.3238. Min Act: -0.0000

Data Index: 951997 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.1276. Min Act: -0.0000

Data Index: 513011 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.0590. Min Act: -0.0000

Data Index: 1725802 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.1950. Min Act: -0.0000

Data Index: 923685 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 5.1861. Min Range: -5.1861

Max Act: 3.8449. Min Act: -0.0000

Data Index: 506933 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.0137. Min Act: -0.0000

Data Index: 1785824 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 5.1861. Min Range: -5.1861

Max Act: 3.9225. Min Act: -0.0000

Data Index: 1984414 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.0588. Min Act: -0.0000

Data Index: 842516 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 5.1861. Min Range: -5.1861

Max Act: 3.4070. Min Act: -0.0000

Data Index: 916348 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.0333. Min Act: -0.0000

Data Index: 1847316 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.0063. Min Act: -0.0000

Data Index: 1758016 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 5.1861. Min Range: -5.1861

Max Act: 3.9856. Min Act: -0.0000

Data Index: 801348 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 5.1861. Min Range: -5.1861

Max Act: 3.9374. Min Act: -0.0000

Data Index: 461833 (The Pile)

Max Activating Token Index: 242

Text #17

Max Range: 5.1861. Min Range: -5.1861

Max Act: 3.9130. Min Act: -0.0000

Data Index: 781765 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 5.1861. Min Range: -5.1861

Max Act: 3.7198. Min Act: -0.0000

Data Index: 402553 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 5.1861. Min Range: -5.1861

Max Act: 4.0207. Min Act: -0.0000

Data Index: 2557 (The Pile)

Max Activating Token Index: 967