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

Dataset: The Pile

Neuron 3810 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: 1.8164. Min Range: -1.8164

Max Act: 1.8164. Min Act: -0.0000

Data Index: 1720411 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.5385. Min Act: -0.0000

Data Index: 349200 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.6917. Min Act: -0.0000

Data Index: 1322802 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.6902. Min Act: -0.0000

Data Index: 692344 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.6825. Min Act: -0.0000

Data Index: 141795 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.6587. Min Act: -0.0000

Data Index: 866352 (The Pile)

Max Activating Token Index: 455

Text #6

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.7507. Min Act: -0.0000

Data Index: 1570748 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.6325. Min Act: -0.0000

Data Index: 1721658 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.6055. Min Act: -0.0000

Data Index: 1063570 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1316794 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.6793. Min Act: -0.0000

Data Index: 1144154 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.5640. Min Act: -0.0000

Data Index: 635606 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.5707. Min Act: -0.0000

Data Index: 390538 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.4177. Min Act: -0.0000

Data Index: 810017 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.5135. Min Act: -0.0000

Data Index: 1147724 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.4888. Min Act: -0.0000

Data Index: 361553 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1790192 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.3934. Min Act: -0.0000

Data Index: 1974672 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.5572. Min Act: -0.0000

Data Index: 1516922 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 1.8164. Min Range: -1.8164

Max Act: 1.5733. Min Act: -0.0000

Data Index: 731911 (The Pile)

Max Activating Token Index: 860