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

Dataset: The Pile

Neuron 4452 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: 0.9195. Min Range: -0.9195

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1696482 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.4167. Min Act: -0.0000

Data Index: 715485 (The Pile)

Max Activating Token Index: 154

Text #2

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1384090 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1323738 (The Pile)

Max Activating Token Index: 219

Text #4

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1971261 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1881. Min Act: -0.0000

Data Index: 573285 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1043804 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1280. Min Act: -0.0000

Data Index: 4243 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1734. Min Act: -0.0000

Data Index: 722367 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1014331 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1407. Min Act: -0.0000

Data Index: 736081 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1888653 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1156519 (The Pile)

Max Activating Token Index: 868

Text #13

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1002046 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1804369 (The Pile)

Max Activating Token Index: 572

Text #15

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1427. Min Act: -0.0000

Data Index: 627716 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1476759 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1576. Min Act: -0.0000

Data Index: 164876 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1752629 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 0.9195. Min Range: -0.9195

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1996664 (The Pile)

Max Activating Token Index: 980