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

Dataset: The Pile

Neuron 3809 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: 1.9538. Min Range: -1.9538

Max Act: 1.9538. Min Act: -0.0000

Data Index: 293104 (The Pile)

Max Activating Token Index: 789

Text #1

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.7280. Min Act: -0.0000

Data Index: 1047700 (The Pile)

Max Activating Token Index: 865

Text #2

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.6905. Min Act: -0.0000

Data Index: 1432509 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.4205. Min Act: -0.0000

Data Index: 658944 (The Pile)

Max Activating Token Index: 584

Text #4

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1076908 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.4903. Min Act: -0.0000

Data Index: 218261 (The Pile)

Max Activating Token Index: 106

Text #6

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.7157. Min Act: -0.0000

Data Index: 1380627 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.9218. Min Act: -0.0000

Data Index: 1290601 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.7829. Min Act: -0.0000

Data Index: 863068 (The Pile)

Max Activating Token Index: 220

Text #9

Max Range: 1.9538. Min Range: -1.9538

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1033614 (The Pile)

Max Activating Token Index: 699

Text #10

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.5673. Min Act: -0.0000

Data Index: 720660 (The Pile)

Max Activating Token Index: 28

Text #11

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.0548. Min Act: -0.0000

Data Index: 944844 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.6828. Min Act: -0.0000

Data Index: 366632 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.7724. Min Act: -0.0000

Data Index: 97258 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 1.9538. Min Range: -1.9538

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1481786 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1769349 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.6246. Min Act: -0.0000

Data Index: 369101 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 1.9538. Min Range: -1.9538

Max Act: 0.9681. Min Act: -0.0000

Data Index: 1189879 (The Pile)

Max Activating Token Index: 87

Text #18

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.4622. Min Act: -0.0000

Data Index: 732383 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 1.9538. Min Range: -1.9538

Max Act: 1.4441. Min Act: -0.0000

Data Index: 11672 (The Pile)

Max Activating Token Index: 664