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

Dataset: The Pile

Neuron 2911 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: 0.5311. Min Range: -0.5311

Max Act: 0.5311. Min Act: -0.0000

Data Index: 595035 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1493483 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1304759 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.5276. Min Act: -0.0000

Data Index: 166576 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1464613 (The Pile)

Max Activating Token Index: 975

Text #5

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3793. Min Act: -0.0000

Data Index: 439704 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4185. Min Act: -0.0000

Data Index: 105851 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1932190 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1485385 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1270797 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1566830 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4084. Min Act: -0.0000

Data Index: 749055 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3752. Min Act: -0.0000

Data Index: 125153 (The Pile)

Max Activating Token Index: 340

Text #13

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1603734 (The Pile)

Max Activating Token Index: 337

Text #14

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.4366. Min Act: -0.0000

Data Index: 20010 (The Pile)

Max Activating Token Index: 186

Text #15

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3992. Min Act: -0.0000

Data Index: 479401 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3217. Min Act: -0.0000

Data Index: 775776 (The Pile)

Max Activating Token Index: 475

Text #17

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1860806 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.3589. Min Act: -0.0000

Data Index: 578089 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 0.5311. Min Range: -0.5311

Max Act: 0.2727. Min Act: -0.0000

Data Index: 562648 (The Pile)

Max Activating Token Index: 819