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

Dataset: The Pile

Neuron 5114 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: 0.9440. Min Range: -0.9440

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1843326 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1060613 (The Pile)

Max Activating Token Index: 237

Text #2

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.7248. Min Act: 0.0000

Data Index: 1449777 (The Pile)

Max Activating Token Index: 400

Text #3

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1203663 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.7267. Min Act: -0.0000

Data Index: 1585569 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6740. Min Act: -0.0000

Data Index: 599965 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1831875 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6557. Min Act: -0.0000

Data Index: 654938 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1151044 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1638662 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6417. Min Act: -0.0000

Data Index: 666819 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6000. Min Act: -0.0000

Data Index: 791105 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1907661 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1088822 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1541061 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6187. Min Act: -0.0000

Data Index: 532077 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6167. Min Act: -0.0000

Data Index: 285174 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.5936. Min Act: 0.0000

Data Index: 943556 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1622698 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.9440. Min Range: -0.9440

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1572397 (The Pile)

Max Activating Token Index: 431