Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 18 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0116. Min Range: -1.0116

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1163801 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1682532 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 1.0116. Min Range: -1.0116

Max Act: 1.0116. Min Act: 0.0000

Data Index: 702431 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8552. Min Act: 0.0002

Data Index: 1907220 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1138439 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8032. Min Act: 0.0000

Data Index: 1031972 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7993. Min Act: 0.0000

Data Index: 571602 (The Pile)

Max Activating Token Index: 556

Text #7

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1331159 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7871. Min Act: -0.0000

Data Index: 952522 (The Pile)

Max Activating Token Index: 720

Text #9

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8344. Min Act: -0.0000

Data Index: 986115 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8260. Min Act: -0.0000

Data Index: 535046 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1921011 (The Pile)

Max Activating Token Index: 885

Text #12

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7474. Min Act: -0.0000

Data Index: 703759 (The Pile)

Max Activating Token Index: 22

Text #13

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.8775. Min Act: -0.0000

Data Index: 497814 (The Pile)

Max Activating Token Index: 695

Text #14

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7545. Min Act: -0.0000

Data Index: 668559 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7961. Min Act: -0.0000

Data Index: 343464 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7171. Min Act: 0.0003

Data Index: 937521 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7155. Min Act: 0.0000

Data Index: 45420 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7614. Min Act: -0.0000

Data Index: 112263 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 1.0116. Min Range: -1.0116

Max Act: 0.7536. Min Act: -0.0000

Data Index: 1708016 (The Pile)

Max Activating Token Index: 842