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

Dataset: The Pile

Neuron 3676 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: 1.9477. Min Range: -1.9477

Max Act: 1.9477. Min Act: -0.0000

Data Index: 219215 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.4494. Min Act: -0.0000

Data Index: 328260 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.1229. Min Act: -0.0000

Data Index: 495619 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.0229. Min Act: -0.0000

Data Index: 555652 (The Pile)

Max Activating Token Index: 490

Text #4

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1339459 (The Pile)

Max Activating Token Index: 992

Text #5

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.0510. Min Act: -0.0000

Data Index: 1496756 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1102279 (The Pile)

Max Activating Token Index: 48

Text #7

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.0241. Min Act: -0.0000

Data Index: 663279 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.0220. Min Act: -0.0000

Data Index: 1343726 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 1.9477. Min Range: -1.9477

Max Act: 1.0007. Min Act: -0.0000

Data Index: 394220 (The Pile)

Max Activating Token Index: 232

Text #10

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1666339 (The Pile)

Max Activating Token Index: 531

Text #11

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1942164 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1257654 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.9060. Min Act: -0.0000

Data Index: 180866 (The Pile)

Max Activating Token Index: 394

Text #14

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1658001 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1968615 (The Pile)

Max Activating Token Index: 898

Text #16

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.8799. Min Act: -0.0000

Data Index: 426041 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.9073. Min Act: -0.0000

Data Index: 563172 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.8335. Min Act: -0.0000

Data Index: 333629 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 1.9477. Min Range: -1.9477

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1086145 (The Pile)

Max Activating Token Index: 244