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

Dataset: The Pile

Neuron 2219 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: 0.4327. Min Range: -0.4327

Max Act: 0.4327. Min Act: -0.0000

Data Index: 1294052 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1721335 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3867. Min Act: -0.0000

Data Index: 728863 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.4163. Min Act: -0.0000

Data Index: 261370 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3978. Min Act: -0.0000

Data Index: 839924 (The Pile)

Max Activating Token Index: 234

Text #5

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3653. Min Act: -0.0000

Data Index: 263350 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3778. Min Act: -0.0000

Data Index: 141072 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1178314 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1394588 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1584472 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1598848 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3462. Min Act: -0.0000

Data Index: 868362 (The Pile)

Max Activating Token Index: 875

Text #12

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1896997 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3522. Min Act: -0.0000

Data Index: 483235 (The Pile)

Max Activating Token Index: 466

Text #14

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3680. Min Act: -0.0000

Data Index: 521282 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3573. Min Act: -0.0000

Data Index: 117089 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3241. Min Act: -0.0000

Data Index: 950039 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1656218 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1424549 (The Pile)

Max Activating Token Index: 858

Text #19

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3564. Min Act: -0.0000

Data Index: 726623 (The Pile)

Max Activating Token Index: 633