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

Dataset: The Pile

Neuron 2428 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: 0.1410. Min Range: -0.1410

Max Act: 0.1330. Min Act: -0.0000

Data Index: 1752855 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1410. Min Act: -0.0000

Data Index: 434515 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1115. Min Act: -0.0000

Data Index: 525198 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1054. Min Act: -0.0000

Data Index: 907161 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1259546 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1039. Min Act: -0.0000

Data Index: 763917 (The Pile)

Max Activating Token Index: 434

Text #6

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0829. Min Act: -0.0000

Data Index: 839194 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1102384 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0966. Min Act: -0.0000

Data Index: 903520 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1705091 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0705. Min Act: -0.0000

Data Index: 94875 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0693. Min Act: -0.0000

Data Index: 1611695 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0650. Min Act: 0.0000

Data Index: 1914262 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0711. Min Act: -0.0000

Data Index: 549942 (The Pile)

Max Activating Token Index: 302

Text #14

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0784. Min Act: -0.0000

Data Index: 119983 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0673. Min Act: -0.0000

Data Index: 184831 (The Pile)

Max Activating Token Index: 664

Text #16

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1183395 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1223671 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1105269 (The Pile)

Max Activating Token Index: 827

Text #19

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0710. Min Act: -0.0000

Data Index: 878479 (The Pile)

Max Activating Token Index: 820