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

Dataset: The Pile

Neuron 418 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: 0.2185. Min Range: -0.2185

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1410493 (The Pile)

Max Activating Token Index: 515

Text #1

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1834. Min Act: -0.0000

Data Index: 1799101 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1053470 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1661952 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1744. Min Act: -0.0000

Data Index: 443180 (The Pile)

Max Activating Token Index: 449

Text #5

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1640. Min Act: -0.0000

Data Index: 477277 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1189412 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1686. Min Act: -0.0000

Data Index: 277962 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1468. Min Act: -0.0000

Data Index: 809873 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1443. Min Act: -0.0000

Data Index: 460387 (The Pile)

Max Activating Token Index: 83

Text #10

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1792593 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1455. Min Act: -0.0000

Data Index: 433019 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1490. Min Act: -0.0000

Data Index: 85178 (The Pile)

Max Activating Token Index: 118

Text #13

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1233. Min Act: -0.0000

Data Index: 1148996 (The Pile)

Max Activating Token Index: 642

Text #14

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1883045 (The Pile)

Max Activating Token Index: 552

Text #15

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1220. Min Act: -0.0000

Data Index: 388711 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1326. Min Act: -0.0000

Data Index: 974798 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1169020 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1268. Min Act: -0.0000

Data Index: 532695 (The Pile)

Max Activating Token Index: 638

Text #19

Max Range: 0.2185. Min Range: -0.2185

Max Act: 0.1348. Min Act: -0.0000

Data Index: 577747 (The Pile)

Max Activating Token Index: 367