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

Dataset: The Pile

Neuron 1440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.9081. Min Act: -0.0000

Data Index: 1418630 (The Pile)

Max Activating Token Index: 422

Text #1

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.9252. Min Act: -0.0000

Data Index: 788261 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8380. Min Act: -0.0000

Data Index: 845249 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7497. Min Act: -0.0000

Data Index: 310693 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8047. Min Act: -0.0000

Data Index: 512476 (The Pile)

Max Activating Token Index: 935

Text #5

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1180883 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7543. Min Act: -0.0000

Data Index: 733039 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8393. Min Act: -0.0000

Data Index: 890221 (The Pile)

Max Activating Token Index: 488

Text #8

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.8569. Min Act: -0.0000

Data Index: 793000 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7568. Min Act: -0.0000

Data Index: 692160 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7844. Min Act: -0.0000

Data Index: 782666 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7746. Min Act: -0.0000

Data Index: 1562991 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7650. Min Act: -0.0000

Data Index: 666165 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1054050 (The Pile)

Max Activating Token Index: 246

Text #14

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.6776. Min Act: -0.0000

Data Index: 192151 (The Pile)

Max Activating Token Index: 200

Text #15

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1850877 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7819. Min Act: -0.0000

Data Index: 551400 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7195. Min Act: -0.0000

Data Index: 687797 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.7180. Min Act: -0.0000

Data Index: 320792 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 0.9252. Min Range: -0.9252

Max Act: 0.6282. Min Act: -0.0000

Data Index: 864006 (The Pile)

Max Activating Token Index: 97