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

Dataset: The Pile

Neuron 213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0030. Min Range: -3.0030

Max Act: 3.0030. Min Act: -0.0000

Data Index: 767932 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.7723. Min Act: -0.0000

Data Index: 1191752 (The Pile)

Max Activating Token Index: 296

Text #2

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.9843. Min Act: -0.0000

Data Index: 877555 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.7094. Min Act: -0.0000

Data Index: 59776 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5758. Min Act: -0.0000

Data Index: 392237 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4828. Min Act: -0.0000

Data Index: 543016 (The Pile)

Max Activating Token Index: 164

Text #6

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4302. Min Act: -0.0000

Data Index: 604510 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6709. Min Act: -0.0000

Data Index: 1595538 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.7607. Min Act: -0.0000

Data Index: 1552519 (The Pile)

Max Activating Token Index: 803

Text #9

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4887. Min Act: -0.0000

Data Index: 1641386 (The Pile)

Max Activating Token Index: 967

Text #10

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3525. Min Act: -0.0000

Data Index: 1307524 (The Pile)

Max Activating Token Index: 446

Text #11

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3074. Min Act: -0.0000

Data Index: 1007496 (The Pile)

Max Activating Token Index: 795

Text #12

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4491. Min Act: -0.0000

Data Index: 1367462 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3977. Min Act: -0.0000

Data Index: 818554 (The Pile)

Max Activating Token Index: 460

Text #14

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3685. Min Act: -0.0000

Data Index: 1887747 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.1323. Min Act: -0.0000

Data Index: 1691199 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3269. Min Act: -0.0000

Data Index: 1718116 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4549. Min Act: -0.0000

Data Index: 1850393 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4225. Min Act: -0.0000

Data Index: 803335 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.2766. Min Act: -0.0000

Data Index: 253008 (The Pile)

Max Activating Token Index: 16