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

Dataset: The Pile

Neuron 5016 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: 0.8679. Min Range: -0.8679

Max Act: 0.8679. Min Act: 0.0000

Data Index: 1137677 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.8600. Min Act: -0.0000

Data Index: 44781 (The Pile)

Max Activating Token Index: 955

Text #2

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1859037 (The Pile)

Max Activating Token Index: 800

Text #3

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7704. Min Act: -0.0000

Data Index: 1969602 (The Pile)

Max Activating Token Index: 579

Text #4

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1435459 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7142. Min Act: 0.0000

Data Index: 171493 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1576536 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1944754 (The Pile)

Max Activating Token Index: 747

Text #8

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6857. Min Act: -0.0000

Data Index: 853809 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1831975 (The Pile)

Max Activating Token Index: 137

Text #10

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6773. Min Act: -0.0000

Data Index: 319632 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7066. Min Act: -0.0000

Data Index: 903550 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1017164 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6696. Min Act: -0.0000

Data Index: 163132 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1361961 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1281522 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6333. Min Act: -0.0000

Data Index: 380493 (The Pile)

Max Activating Token Index: 836

Text #17

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6433. Min Act: -0.0000

Data Index: 182849 (The Pile)

Max Activating Token Index: 943

Text #18

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.5779. Min Act: 0.0000

Data Index: 1201920 (The Pile)

Max Activating Token Index: 365

Text #19

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1791106 (The Pile)

Max Activating Token Index: 445