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

Dataset: The Pile

Neuron 1573 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1212599 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2694. Min Act: -0.0000

Data Index: 768973 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1867653 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2446. Min Act: -0.0000

Data Index: 619901 (The Pile)

Max Activating Token Index: 414

Text #4

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2426. Min Act: 0.0000

Data Index: 1921029 (The Pile)

Max Activating Token Index: 163

Text #5

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2385. Min Act: -0.0000

Data Index: 453265 (The Pile)

Max Activating Token Index: 807

Text #6

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2084. Min Act: -0.0000

Data Index: 12857 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1081462 (The Pile)

Max Activating Token Index: 776

Text #8

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2338. Min Act: -0.0000

Data Index: 206910 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2181. Min Act: -0.0000

Data Index: 570450 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1690318 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1256318 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2226. Min Act: -0.0000

Data Index: 487843 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2102. Min Act: -0.0000

Data Index: 711509 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2155. Min Act: -0.0000

Data Index: 680463 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2225. Min Act: -0.0000

Data Index: 1894068 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2207. Min Act: -0.0000

Data Index: 732527 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1245905 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2059. Min Act: -0.0000

Data Index: 34883 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 0.2752. Min Range: -0.2752

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1659805 (The Pile)

Max Activating Token Index: 247