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

Dataset: The Pile

Neuron 4680 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.5485. Min Act: -0.0000

Data Index: 695493 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.9588. Min Act: -0.0000

Data Index: 748116 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.4191. Min Act: -0.0000

Data Index: 234978 (The Pile)

Max Activating Token Index: 909

Text #3

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.8617. Min Act: -0.0000

Data Index: 1428697 (The Pile)

Max Activating Token Index: 923

Text #4

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.5746. Min Act: -0.0000

Data Index: 175144 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.4307. Min Act: -0.0000

Data Index: 1062588 (The Pile)

Max Activating Token Index: 415

Text #6

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.4005. Min Act: -0.0000

Data Index: 1024226 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.5580. Min Act: -0.0000

Data Index: 862712 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1422979 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.5299. Min Act: -0.0000

Data Index: 30754 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1815602 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.5316. Min Act: -0.0000

Data Index: 53784 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.3864. Min Act: -0.0000

Data Index: 829823 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.2909. Min Act: -0.0000

Data Index: 304262 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.4479. Min Act: -0.0000

Data Index: 1518230 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.2840. Min Act: -0.0000

Data Index: 811405 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.2192. Min Act: -0.0000

Data Index: 433513 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.3768. Min Act: -0.0000

Data Index: 1129908 (The Pile)

Max Activating Token Index: 650

Text #18

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.2240. Min Act: -0.0000

Data Index: 732072 (The Pile)

Max Activating Token Index: 842

Text #19

Max Range: 1.9588. Min Range: -1.9588

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1441878 (The Pile)

Max Activating Token Index: 345