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

Dataset: The Pile

Neuron 4897 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.7656. Min Act: -0.0000

Data Index: 788908 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.7269. Min Act: -0.0000

Data Index: 393902 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.7026. Min Act: -0.0000

Data Index: 253600 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.6752. Min Act: -0.0000

Data Index: 1646688 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5158. Min Act: -0.0000

Data Index: 10287 (The Pile)

Max Activating Token Index: 12

Text #5

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1881516 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5613. Min Act: -0.0000

Data Index: 174173 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1057549 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5607. Min Act: -0.0000

Data Index: 1592588 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.4652. Min Act: -0.0000

Data Index: 6659 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.6162. Min Act: -0.0000

Data Index: 1026105 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5618. Min Act: -0.0000

Data Index: 26401 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5962. Min Act: -0.0000

Data Index: 957786 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5067. Min Act: -0.0000

Data Index: 99677 (The Pile)

Max Activating Token Index: 6

Text #14

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.4287. Min Act: -0.0000

Data Index: 1144584 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1616793 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5896. Min Act: -0.0000

Data Index: 1521267 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.4924. Min Act: -0.0000

Data Index: 487693 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.5415. Min Act: -0.0000

Data Index: 1566944 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 1.7656. Min Range: -1.7656

Max Act: 1.4503. Min Act: -0.0000

Data Index: 111964 (The Pile)

Max Activating Token Index: 324