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

Dataset: The Pile

Neuron 4836 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: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0000

Data Index: 445599 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1964734 (The Pile)

Max Activating Token Index: 417

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1487571 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1765578 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7314. Min Act: -0.0000

Data Index: 461498 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6803. Min Act: -0.0000

Data Index: 30181 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1524210 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1114967 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1690686 (The Pile)

Max Activating Token Index: 36

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1823764 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7028. Min Act: -0.0000

Data Index: 635258 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6714. Min Act: -0.0000

Data Index: 972353 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1750635 (The Pile)

Max Activating Token Index: 88

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6657. Min Act: -0.0000

Data Index: 1593239 (The Pile)

Max Activating Token Index: 77

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6703. Min Act: -0.0000

Data Index: 390849 (The Pile)

Max Activating Token Index: 141

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1188580 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6545. Min Act: -0.0000

Data Index: 817142 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6749. Min Act: -0.0000

Data Index: 480405 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6922. Min Act: -0.0000

Data Index: 44764 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1754988 (The Pile)

Max Activating Token Index: 474