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

Dataset: The Pile

Neuron 1393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.6896. Min Act: -0.0000

Data Index: 1606746 (The Pile)

Max Activating Token Index: 95

Text #1

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5785. Min Act: -0.0000

Data Index: 268285 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5515. Min Act: -0.0000

Data Index: 595136 (The Pile)

Max Activating Token Index: 904

Text #3

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5381. Min Act: -0.0000

Data Index: 165677 (The Pile)

Max Activating Token Index: 406

Text #4

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1959404 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5221. Min Act: -0.0000

Data Index: 213835 (The Pile)

Max Activating Token Index: 544

Text #6

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5081. Min Act: -0.0000

Data Index: 655460 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1447419 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4562. Min Act: -0.0000

Data Index: 143703 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1340207 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.5265. Min Act: -0.0000

Data Index: 1404623 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4803. Min Act: -0.0000

Data Index: 191825 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1821110 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4330. Min Act: -0.0000

Data Index: 39515 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4680. Min Act: -0.0000

Data Index: 1356233 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1437700 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4171. Min Act: -0.0000

Data Index: 1240304 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4164. Min Act: -0.0000

Data Index: 591390 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4585. Min Act: -0.0000

Data Index: 689230 (The Pile)

Max Activating Token Index: 233

Text #19

Max Range: 1.6896. Min Range: -1.6896

Max Act: 1.4476. Min Act: -0.0000

Data Index: 206543 (The Pile)

Max Activating Token Index: 64