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

Dataset: The Pile

Neuron 305 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1277815 (The Pile)

Max Activating Token Index: 224

Text #1

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1981171 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0914. Min Act: -0.0000

Data Index: 144881 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1759573 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1819897 (The Pile)

Max Activating Token Index: 239

Text #5

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0737. Min Act: -0.0000

Data Index: 310719 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0812. Min Act: -0.0000

Data Index: 1842252 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1336011 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0718. Min Act: -0.0000

Data Index: 717479 (The Pile)

Max Activating Token Index: 118

Text #9

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0744. Min Act: -0.0000

Data Index: 736386 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0682. Min Act: -0.0000

Data Index: 773948 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1307661 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0750. Min Act: -0.0000

Data Index: 943004 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1995003 (The Pile)

Max Activating Token Index: 911

Text #14

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0634. Min Act: -0.0000

Data Index: 869282 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1384284 (The Pile)

Max Activating Token Index: 1005

Text #16

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1806778 (The Pile)

Max Activating Token Index: 149

Text #17

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0636. Min Act: -0.0000

Data Index: 756333 (The Pile)

Max Activating Token Index: 782

Text #18

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1664208 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.1312. Min Range: -0.1312

Max Act: 0.0661. Min Act: -0.0000

Data Index: 591661 (The Pile)

Max Activating Token Index: 561