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

Dataset: The Pile

Neuron 3304 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: 5.8026. Min Range: -5.8026

Max Act: 5.6819. Min Act: -0.0000

Data Index: 1446740 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 5.8026. Min Range: -5.8026

Max Act: 4.7675. Min Act: -0.0000

Data Index: 1238643 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.8026. Min Act: -0.0000

Data Index: 968792 (The Pile)

Max Activating Token Index: 991

Text #3

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.4785. Min Act: -0.0000

Data Index: 1042440 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.6179. Min Act: -0.0000

Data Index: 1345864 (The Pile)

Max Activating Token Index: 577

Text #5

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.7283. Min Act: -0.0000

Data Index: 1080828 (The Pile)

Max Activating Token Index: 546

Text #6

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.3788. Min Act: -0.0000

Data Index: 402766 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.3304. Min Act: -0.0000

Data Index: 972078 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.5136. Min Act: -0.0000

Data Index: 1212433 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 5.8026. Min Range: -5.8026

Max Act: 4.8613. Min Act: -0.0000

Data Index: 1177825 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.1308. Min Act: -0.0000

Data Index: 643721 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.1451. Min Act: -0.0000

Data Index: 1541714 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.4413. Min Act: -0.0000

Data Index: 707419 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.2753. Min Act: -0.0000

Data Index: 196553 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.5603. Min Act: -0.0000

Data Index: 272628 (The Pile)

Max Activating Token Index: 896

Text #15

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.3727. Min Act: -0.0000

Data Index: 1064609 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.2937. Min Act: -0.0000

Data Index: 737631 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.5365. Min Act: -0.0000

Data Index: 629951 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 5.8026. Min Range: -5.8026

Max Act: 5.5203. Min Act: -0.0000

Data Index: 1152041 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 5.8026. Min Range: -5.8026

Max Act: 4.9223. Min Act: -0.0000

Data Index: 1137859 (The Pile)

Max Activating Token Index: 550