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

Dataset: The Pile

Neuron 516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1210. Min Range: -1.1210

Max Act: 1.1210. Min Act: -0.0000

Data Index: 703293 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 1.1210. Min Range: -1.1210

Max Act: 1.0970. Min Act: -0.0000

Data Index: 1049948 (The Pile)

Max Activating Token Index: 400

Text #2

Max Range: 1.1210. Min Range: -1.1210

Max Act: 1.0596. Min Act: -0.0000

Data Index: 278409 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 1.1210. Min Range: -1.1210

Max Act: 1.0445. Min Act: -0.0000

Data Index: 635324 (The Pile)

Max Activating Token Index: 676

Text #4

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1631915 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9390. Min Act: -0.0000

Data Index: 982981 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9123. Min Act: -0.0000

Data Index: 125617 (The Pile)

Max Activating Token Index: 598

Text #7

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1082193 (The Pile)

Max Activating Token Index: 718

Text #8

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9665. Min Act: -0.0000

Data Index: 467123 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9511. Min Act: -0.0000

Data Index: 114703 (The Pile)

Max Activating Token Index: 789

Text #10

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1765525 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8934. Min Act: -0.0000

Data Index: 637747 (The Pile)

Max Activating Token Index: 81

Text #12

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8182. Min Act: -0.0000

Data Index: 627936 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1515533 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1256973 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1845629 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8252. Min Act: -0.0000

Data Index: 503527 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1368738 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8261. Min Act: -0.0000

Data Index: 1580095 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1637866 (The Pile)

Max Activating Token Index: 198