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

Dataset: The Pile

Neuron 1725 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: 1.7795. Min Range: -1.7795

Max Act: 1.7795. Min Act: -0.0000

Data Index: 836777 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.6479. Min Act: -0.0000

Data Index: 1311137 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1390826 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.4693. Min Act: -0.0000

Data Index: 1443969 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.4689. Min Act: -0.0000

Data Index: 293401 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.4604. Min Act: -0.0000

Data Index: 920086 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.3618. Min Act: -0.0000

Data Index: 866938 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.3536. Min Act: -0.0000

Data Index: 487086 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.4829. Min Act: -0.0000

Data Index: 1104379 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1739626 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2488. Min Act: -0.0000

Data Index: 693620 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1668835 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2217. Min Act: -0.0000

Data Index: 47844 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.3643. Min Act: -0.0000

Data Index: 1263501 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.3523. Min Act: -0.0000

Data Index: 541498 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2019. Min Act: -0.0000

Data Index: 608898 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2752. Min Act: -0.0000

Data Index: 591821 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2614. Min Act: -0.0000

Data Index: 1846183 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.2578. Min Act: -0.0000

Data Index: 295019 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 1.7795. Min Range: -1.7795

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1425407 (The Pile)

Max Activating Token Index: 864