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

Dataset: The Pile

Neuron 3641 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.5659. Min Act: -0.0000

Data Index: 427300 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.5121. Min Act: -0.0000

Data Index: 220975 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4691. Min Act: -0.0000

Data Index: 80925 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1047840 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1861753 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4304. Min Act: -0.0000

Data Index: 1562687 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4177. Min Act: -0.0000

Data Index: 271483 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4280. Min Act: -0.0000

Data Index: 1096391 (The Pile)

Max Activating Token Index: 328

Text #8

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.4081. Min Act: -0.0000

Data Index: 525696 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3821. Min Act: -0.0000

Data Index: 956396 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3892. Min Act: -0.0000

Data Index: 419797 (The Pile)

Max Activating Token Index: 310

Text #11

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3764. Min Act: -0.0000

Data Index: 237633 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3790. Min Act: -0.0000

Data Index: 989276 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3721. Min Act: -0.0000

Data Index: 321684 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1659181 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1158712 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3427. Min Act: -0.0000

Data Index: 32486 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3472. Min Act: -0.0000

Data Index: 336109 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3643. Min Act: -0.0000

Data Index: 961543 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.5659. Min Range: -0.5659

Max Act: 0.3524. Min Act: -0.0000

Data Index: 885747 (The Pile)

Max Activating Token Index: 293