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

Dataset: The Pile

Neuron 4665 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: 1.2417. Min Range: -1.2417

Max Act: 1.2417. Min Act: -0.0000

Data Index: 475042 (The Pile)

Max Activating Token Index: 442

Text #1

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.1989. Min Act: -0.0000

Data Index: 128860 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.1336. Min Act: -0.0000

Data Index: 441667 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.0269. Min Act: -0.0000

Data Index: 714824 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.0607. Min Act: -0.0000

Data Index: 150193 (The Pile)

Max Activating Token Index: 692

Text #5

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.0290. Min Act: -0.0000

Data Index: 790993 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.0087. Min Act: -0.0000

Data Index: 258993 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 1.2417. Min Range: -1.2417

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1751473 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9295. Min Act: -0.0000

Data Index: 458082 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9808. Min Act: -0.0000

Data Index: 870585 (The Pile)

Max Activating Token Index: 473

Text #10

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9667. Min Act: -0.0000

Data Index: 274566 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1123815 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9525. Min Act: -0.0000

Data Index: 632651 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8793. Min Act: -0.0000

Data Index: 1578616 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8589. Min Act: -0.0000

Data Index: 1257820 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1786085 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8857. Min Act: -0.0000

Data Index: 1505758 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1398084 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.8619. Min Act: -0.0000

Data Index: 258726 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.2417. Min Range: -1.2417

Max Act: 0.9119. Min Act: -0.0000

Data Index: 654973 (The Pile)

Max Activating Token Index: 862