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

Dataset: The Pile

Neuron 529 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2109. Min Range: -3.2109

Max Act: 3.1742. Min Act: -0.0000

Data Index: 1968495 (The Pile)

Max Activating Token Index: 895

Text #1

Max Range: 3.2109. Min Range: -3.2109

Max Act: 3.1809. Min Act: -0.0000

Data Index: 1425253 (The Pile)

Max Activating Token Index: 916

Text #2

Max Range: 3.2109. Min Range: -3.2109

Max Act: 3.0302. Min Act: -0.0000

Data Index: 613463 (The Pile)

Max Activating Token Index: 865

Text #3

Max Range: 3.2109. Min Range: -3.2109

Max Act: 3.2109. Min Act: -0.0000

Data Index: 1185372 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.5852. Min Act: -0.0000

Data Index: 1558857 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.8525. Min Act: -0.0000

Data Index: 1679334 (The Pile)

Max Activating Token Index: 947

Text #6

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.6088. Min Act: -0.0000

Data Index: 212119 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.6561. Min Act: -0.0000

Data Index: 1677206 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.8268. Min Act: -0.0000

Data Index: 810499 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.5359. Min Act: -0.0000

Data Index: 923904 (The Pile)

Max Activating Token Index: 996

Text #10

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.5394. Min Act: -0.0000

Data Index: 1594579 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.7197. Min Act: -0.0000

Data Index: 227608 (The Pile)

Max Activating Token Index: 979

Text #12

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.7279. Min Act: -0.0000

Data Index: 1925294 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.2795. Min Act: -0.0000

Data Index: 1696593 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 3.2109. Min Range: -3.2109

Max Act: 1.8153. Min Act: -0.0000

Data Index: 969247 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.2616. Min Act: -0.0000

Data Index: 612492 (The Pile)

Max Activating Token Index: 873

Text #16

Max Range: 3.2109. Min Range: -3.2109

Max Act: 1.9981. Min Act: -0.0000

Data Index: 41672 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.3623. Min Act: -0.0000

Data Index: 165953 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.2294. Min Act: -0.0000

Data Index: 1009749 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 3.2109. Min Range: -3.2109

Max Act: 2.4576. Min Act: -0.0000

Data Index: 1753784 (The Pile)

Max Activating Token Index: 857