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

Dataset: The Pile

Neuron 3918 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: 0.3080. Min Range: -0.3080

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1626364 (The Pile)

Max Activating Token Index: 623

Text #1

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1561372 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2891. Min Act: -0.0000

Data Index: 245438 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2753. Min Act: -0.0000

Data Index: 1661846 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2790. Min Act: -0.0000

Data Index: 1901162 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2491. Min Act: -0.0000

Data Index: 877362 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1867325 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1675430 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2553. Min Act: -0.0000

Data Index: 958072 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1462580 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1665814 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2498. Min Act: -0.0000

Data Index: 568084 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1079525 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2403. Min Act: -0.0000

Data Index: 765099 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2034. Min Act: -0.0000

Data Index: 708969 (The Pile)

Max Activating Token Index: 725

Text #15

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2271. Min Act: -0.0000

Data Index: 1084417 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2002. Min Act: -0.0000

Data Index: 345624 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2520. Min Act: -0.0000

Data Index: 104280 (The Pile)

Max Activating Token Index: 422

Text #18

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2256. Min Act: -0.0000

Data Index: 10774 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1104028 (The Pile)

Max Activating Token Index: 895