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

Dataset: The Pile

Neuron 3963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4036. Min Range: -4.4036

Max Act: 4.4036. Min Act: -0.0000

Data Index: 154352 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 4.4036. Min Range: -4.4036

Max Act: 4.1605. Min Act: -0.0000

Data Index: 1585285 (The Pile)

Max Activating Token Index: 247

Text #2

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.9760. Min Act: -0.0000

Data Index: 570659 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.9068. Min Act: -0.0000

Data Index: 1981955 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 4.4036. Min Range: -4.4036

Max Act: 4.0175. Min Act: -0.0000

Data Index: 923767 (The Pile)

Max Activating Token Index: 111

Text #5

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.8650. Min Act: -0.0000

Data Index: 841723 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.8067. Min Act: -0.0000

Data Index: 1968620 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.7279. Min Act: -0.0000

Data Index: 1652074 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.6548. Min Act: -0.0000

Data Index: 73140 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.6677. Min Act: -0.0000

Data Index: 394609 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.5047. Min Act: -0.0000

Data Index: 1451782 (The Pile)

Max Activating Token Index: 969

Text #11

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.4064. Min Act: -0.0000

Data Index: 27987 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.5396. Min Act: -0.0000

Data Index: 926285 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.3761. Min Act: -0.0000

Data Index: 241712 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.3765. Min Act: -0.0000

Data Index: 883023 (The Pile)

Max Activating Token Index: 830

Text #15

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.2683. Min Act: -0.0000

Data Index: 1367670 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.3738. Min Act: -0.0000

Data Index: 1693779 (The Pile)

Max Activating Token Index: 104

Text #17

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.3750. Min Act: -0.0000

Data Index: 1124218 (The Pile)

Max Activating Token Index: 226

Text #18

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.3463. Min Act: -0.0000

Data Index: 886567 (The Pile)

Max Activating Token Index: 886

Text #19

Max Range: 4.4036. Min Range: -4.4036

Max Act: 3.3225. Min Act: -0.0000

Data Index: 796734 (The Pile)

Max Activating Token Index: 80