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

Dataset: The Pile

Neuron 1380 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: 0.5432. Min Range: -0.5432

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1766291 (The Pile)

Max Activating Token Index: 775

Text #1

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1135572 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4174. Min Act: -0.0000

Data Index: 191740 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1030290 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3588. Min Act: -0.0000

Data Index: 196148 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3941. Min Act: -0.0000

Data Index: 972678 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4431. Min Act: -0.0000

Data Index: 267987 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1377133 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1756341 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1631169 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1069552 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1157684 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1511749 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1617106 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.2907. Min Act: -0.0000

Data Index: 693413 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1567757 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3901. Min Act: -0.0000

Data Index: 508378 (The Pile)

Max Activating Token Index: 400

Text #17

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1772619 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3736. Min Act: -0.0000

Data Index: 599780 (The Pile)

Max Activating Token Index: 155

Text #19

Max Range: 0.5432. Min Range: -0.5432

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1477336 (The Pile)

Max Activating Token Index: 931