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

Dataset: The Pile

Neuron 3704 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: 0.8310. Min Range: -0.8310

Max Act: 0.8310. Min Act: -0.0000

Data Index: 940691 (The Pile)

Max Activating Token Index: 979

Text #1

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.7854. Min Act: -0.0000

Data Index: 847252 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.7205. Min Act: -0.0000

Data Index: 863116 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.6684. Min Act: -0.0000

Data Index: 796956 (The Pile)

Max Activating Token Index: 974

Text #4

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.6137. Min Act: -0.0000

Data Index: 164835 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1815373 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4718. Min Act: -0.0000

Data Index: 569945 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4407. Min Act: -0.0000

Data Index: 195770 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1976006 (The Pile)

Max Activating Token Index: 843

Text #9

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.4737. Min Act: -0.0000

Data Index: 682661 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1116907 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1095966 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3064. Min Act: -0.0000

Data Index: 243874 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3336. Min Act: -0.0000

Data Index: 51568 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1348977 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.2968. Min Act: -0.0000

Data Index: 893762 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1841007 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1947182 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3843. Min Act: -0.0000

Data Index: 392310 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.8310. Min Range: -0.8310

Max Act: 0.3224. Min Act: -0.0000

Data Index: 793573 (The Pile)

Max Activating Token Index: 505