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

Dataset: The Pile

Neuron 1863 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0842. Min Range: -5.0842

Max Act: 5.0842. Min Act: -0.0000

Data Index: 1183162 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 5.0842. Min Range: -5.0842

Max Act: 4.1051. Min Act: -0.0000

Data Index: 1725618 (The Pile)

Max Activating Token Index: 111

Text #2

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.5823. Min Act: -0.0000

Data Index: 1538358 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.7298. Min Act: -0.0000

Data Index: 792357 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.9788. Min Act: -0.0000

Data Index: 547134 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.1284. Min Act: -0.0000

Data Index: 1369009 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 5.0842. Min Range: -5.0842

Max Act: 3.2182. Min Act: -0.0000

Data Index: 889095 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.8457. Min Act: -0.0000

Data Index: 352667 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.8129. Min Act: -0.0000

Data Index: 1211186 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.7383. Min Act: -0.0000

Data Index: 1059959 (The Pile)

Max Activating Token Index: 394

Text #10

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.9040. Min Act: -0.0000

Data Index: 31260 (The Pile)

Max Activating Token Index: 584

Text #11

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.5657. Min Act: -0.0000

Data Index: 864817 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.6348. Min Act: -0.0000

Data Index: 398237 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.6725. Min Act: -0.0000

Data Index: 1145555 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.7300. Min Act: -0.0000

Data Index: 989647 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.4844. Min Act: -0.0000

Data Index: 379340 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.7884. Min Act: -0.0000

Data Index: 986607 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.6436. Min Act: -0.0000

Data Index: 1010611 (The Pile)

Max Activating Token Index: 892

Text #18

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.8913. Min Act: -0.0000

Data Index: 1777367 (The Pile)

Max Activating Token Index: 224

Text #19

Max Range: 5.0842. Min Range: -5.0842

Max Act: 2.6016. Min Act: -0.0000

Data Index: 602470 (The Pile)

Max Activating Token Index: 266