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

Dataset: The Pile

Neuron 2397 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: 1.9265. Min Range: -1.9265

Max Act: 1.9265. Min Act: -0.0000

Data Index: 1643701 (The Pile)

Max Activating Token Index: 264

Text #1

Max Range: 1.9265. Min Range: -1.9265

Max Act: 1.2704. Min Act: -0.0000

Data Index: 318289 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1916333 (The Pile)

Max Activating Token Index: 1007

Text #3

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1218063 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.8525. Min Act: -0.0000

Data Index: 626332 (The Pile)

Max Activating Token Index: 558

Text #5

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1298123 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.8649. Min Act: -0.0000

Data Index: 166247 (The Pile)

Max Activating Token Index: 913

Text #7

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.8817. Min Act: -0.0000

Data Index: 846137 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.9001. Min Act: -0.0000

Data Index: 614260 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1880079 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7846. Min Act: -0.0000

Data Index: 700112 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.8032. Min Act: -0.0000

Data Index: 731321 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7733. Min Act: -0.0000

Data Index: 693684 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7869. Min Act: -0.0000

Data Index: 550411 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7609. Min Act: -0.0000

Data Index: 1611909 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7834. Min Act: -0.0000

Data Index: 658254 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7815. Min Act: -0.0000

Data Index: 257191 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7822. Min Act: -0.0000

Data Index: 944850 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.7815. Min Act: -0.0000

Data Index: 771483 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 1.9265. Min Range: -1.9265

Max Act: 0.6987. Min Act: -0.0000

Data Index: 959032 (The Pile)

Max Activating Token Index: 742