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

Dataset: The Pile

Neuron 959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1706360 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1356279 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7734. Min Act: -0.0000

Data Index: 356184 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7938. Min Act: -0.0000

Data Index: 780571 (The Pile)

Max Activating Token Index: 385

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1436752 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7251. Min Act: -0.0000

Data Index: 509651 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1302448 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1472459 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6490. Min Act: -0.0000

Data Index: 204878 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6668. Min Act: -0.0000

Data Index: 80769 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6555. Min Act: -0.0000

Data Index: 504232 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1106924 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6192. Min Act: -0.0000

Data Index: 124186 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1421559 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1398719 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7272. Min Act: -0.0000

Data Index: 716787 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6558. Min Act: -0.0000

Data Index: 320371 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6397. Min Act: -0.0000

Data Index: 669967 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1628934 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6247. Min Act: -0.0000

Data Index: 107203 (The Pile)

Max Activating Token Index: 326