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

Dataset: The Pile

Neuron 4380 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: 1.7410. Min Range: -1.7410

Max Act: 1.6930. Min Act: -0.0000

Data Index: 815622 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.7410. Min Act: -0.0000

Data Index: 1754859 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.6431. Min Act: -0.0000

Data Index: 1664877 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.6372. Min Act: -0.0000

Data Index: 545497 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.6241. Min Act: -0.0000

Data Index: 952047 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.5032. Min Act: -0.0000

Data Index: 696404 (The Pile)

Max Activating Token Index: 206

Text #6

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.6508. Min Act: -0.0000

Data Index: 1914185 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.4782. Min Act: -0.0000

Data Index: 769770 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.4264. Min Act: -0.0000

Data Index: 1951229 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.3966. Min Act: -0.0000

Data Index: 1277708 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.3876. Min Act: -0.0000

Data Index: 1065192 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.2364. Min Act: 0.0000

Data Index: 126166 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.4484. Min Act: -0.0000

Data Index: 474539 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1786865 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.3233. Min Act: -0.0000

Data Index: 500758 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.3678. Min Act: -0.0000

Data Index: 326653 (The Pile)

Max Activating Token Index: 139

Text #16

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1064607 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.1311. Min Act: -0.0000

Data Index: 726989 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1725414 (The Pile)

Max Activating Token Index: 818

Text #19

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1717028 (The Pile)

Max Activating Token Index: 905