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

Dataset: The Pile

Neuron 366 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.5731. Min Act: -0.0000

Data Index: 391629 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3994. Min Act: -0.0000

Data Index: 313424 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.4604. Min Act: -0.0000

Data Index: 182810 (The Pile)

Max Activating Token Index: 81

Text #3

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.4364. Min Act: -0.0000

Data Index: 734740 (The Pile)

Max Activating Token Index: 501

Text #4

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1533224 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1223830 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3291. Min Act: -0.0000

Data Index: 294817 (The Pile)

Max Activating Token Index: 897

Text #7

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1372138 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2886. Min Act: -0.0000

Data Index: 304736 (The Pile)

Max Activating Token Index: 501

Text #9

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2740. Min Act: -0.0000

Data Index: 1719248 (The Pile)

Max Activating Token Index: 547

Text #10

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2693. Min Act: -0.0000

Data Index: 1850814 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3308. Min Act: -0.0000

Data Index: 251231 (The Pile)

Max Activating Token Index: 160

Text #12

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2628. Min Act: -0.0000

Data Index: 225730 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1911291 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1952095 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2309. Min Act: -0.0000

Data Index: 229825 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1837. Min Act: -0.0000

Data Index: 1275382 (The Pile)

Max Activating Token Index: 935

Text #17

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1006912 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1880. Min Act: -0.0000

Data Index: 886358 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1995285 (The Pile)

Max Activating Token Index: 1019