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

Dataset: The Pile

Neuron 3264 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: 1.8264. Min Range: -1.8264

Max Act: 1.8264. Min Act: -0.0000

Data Index: 1392237 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.7314. Min Act: -0.0000

Data Index: 1613883 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4841. Min Act: -0.0000

Data Index: 506536 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4580. Min Act: -0.0000

Data Index: 133177 (The Pile)

Max Activating Token Index: 93

Text #4

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.5041. Min Act: -0.0000

Data Index: 1798786 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1436812 (The Pile)

Max Activating Token Index: 492

Text #6

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4617. Min Act: -0.0000

Data Index: 1923771 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1688656 (The Pile)

Max Activating Token Index: 11

Text #8

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.4334. Min Act: -0.0000

Data Index: 166262 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1149732 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3245. Min Act: -0.0000

Data Index: 648919 (The Pile)

Max Activating Token Index: 75

Text #11

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3905. Min Act: -0.0000

Data Index: 389664 (The Pile)

Max Activating Token Index: 518

Text #12

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2768. Min Act: -0.0000

Data Index: 1248047 (The Pile)

Max Activating Token Index: 389

Text #13

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2736. Min Act: -0.0000

Data Index: 601980 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1489411 (The Pile)

Max Activating Token Index: 713

Text #15

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1043460 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2377. Min Act: -0.0000

Data Index: 1932079 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1886385 (The Pile)

Max Activating Token Index: 836

Text #18

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1358618 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 1.8264. Min Range: -1.8264

Max Act: 1.2986. Min Act: -0.0000

Data Index: 718326 (The Pile)

Max Activating Token Index: 302