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

Dataset: The Pile

Neuron 1667 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1145176 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1442013 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6315. Min Act: -0.0000

Data Index: 750198 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6667. Min Act: -0.0000

Data Index: 978852 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1431556 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6297. Min Act: -0.0000

Data Index: 481890 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6471. Min Act: -0.0000

Data Index: 196786 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1661511 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1542409 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1342882 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1103654 (The Pile)

Max Activating Token Index: 146

Text #11

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5743. Min Act: -0.0000

Data Index: 943702 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1871911 (The Pile)

Max Activating Token Index: 286

Text #13

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5679. Min Act: -0.0000

Data Index: 1612426 (The Pile)

Max Activating Token Index: 464

Text #14

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1018688 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1040959 (The Pile)

Max Activating Token Index: 131

Text #16

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5800. Min Act: -0.0000

Data Index: 202451 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1914981 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5814. Min Act: -0.0000

Data Index: 405467 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.7575. Min Range: -0.7575

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1750889 (The Pile)

Max Activating Token Index: 141