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

Dataset: The Pile

Neuron 2200 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1773350 (The Pile)

Max Activating Token Index: 262

Text #1

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6802. Min Act: -0.0000

Data Index: 824246 (The Pile)

Max Activating Token Index: 28

Text #2

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.7173. Min Act: -0.0000

Data Index: 863625 (The Pile)

Max Activating Token Index: 343

Text #3

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1143309 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6071. Min Act: -0.0000

Data Index: 547338 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1805338 (The Pile)

Max Activating Token Index: 380

Text #6

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6596. Min Act: -0.0000

Data Index: 907610 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6362. Min Act: -0.0000

Data Index: 1648586 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1921454 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1745082 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1381507 (The Pile)

Max Activating Token Index: 598

Text #11

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6104. Min Act: -0.0000

Data Index: 151758 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6037. Min Act: -0.0000

Data Index: 225290 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1453598 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5840. Min Act: -0.0000

Data Index: 954188 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5570. Min Act: -0.0000

Data Index: 29841 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5930. Min Act: -0.0000

Data Index: 817658 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1660498 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1911434 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 0.7245. Min Range: -0.7245

Max Act: 0.6381. Min Act: -0.0000

Data Index: 1658440 (The Pile)

Max Activating Token Index: 99