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

Dataset: The Pile

Neuron 1018 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1369571 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1290919 (The Pile)

Max Activating Token Index: 686

Text #2

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8884. Min Act: -0.0000

Data Index: 616656 (The Pile)

Max Activating Token Index: 507

Text #3

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1587668 (The Pile)

Max Activating Token Index: 961

Text #4

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8466. Min Act: 0.0000

Data Index: 1806670 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8303. Min Act: -0.0000

Data Index: 870505 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8326. Min Act: -0.0000

Data Index: 207028 (The Pile)

Max Activating Token Index: 54

Text #7

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1608813 (The Pile)

Max Activating Token Index: 792

Text #8

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7935. Min Act: 0.0000

Data Index: 709651 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1985682 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.8017. Min Act: -0.0000

Data Index: 349382 (The Pile)

Max Activating Token Index: 394

Text #11

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7768. Min Act: 0.0000

Data Index: 1653542 (The Pile)

Max Activating Token Index: 706

Text #12

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1776196 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7797. Min Act: -0.0000

Data Index: 554246 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7262. Min Act: -0.0000

Data Index: 293367 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7641. Min Act: -0.0000

Data Index: 881527 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7846. Min Act: -0.0000

Data Index: 771543 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1574232 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.6783. Min Act: -0.0000

Data Index: 893123 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 0.9323. Min Range: -0.9323

Max Act: 0.7098. Min Act: -0.0000

Data Index: 762772 (The Pile)

Max Activating Token Index: 137