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

Dataset: The Pile

Neuron 2826 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1677959 (The Pile)

Max Activating Token Index: 218

Text #1

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1773258 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1642265 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1264887 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.8169. Min Act: -0.0000

Data Index: 11556 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1570781 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1510847 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1390235 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7215. Min Act: -0.0000

Data Index: 205810 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7433. Min Act: -0.0000

Data Index: 994167 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7309. Min Act: -0.0000

Data Index: 86820 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1249073 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6992. Min Act: -0.0000

Data Index: 682236 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1591083 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1962630 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7184. Min Act: -0.0000

Data Index: 417087 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1416124 (The Pile)

Max Activating Token Index: 361

Text #17

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6878. Min Act: -0.0000

Data Index: 280980 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1666373 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 0.9239. Min Range: -0.9239

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1516703 (The Pile)

Max Activating Token Index: 395