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

Dataset: The Pile

Neuron 2272 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: 1.4451. Min Range: -1.4451

Max Act: 1.4451. Min Act: -0.0000

Data Index: 1357014 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.4127. Min Act: -0.0000

Data Index: 1868884 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.3498. Min Act: -0.0000

Data Index: 363367 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1941. Min Act: -0.0000

Data Index: 1401671 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1712293 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2363. Min Act: -0.0000

Data Index: 146437 (The Pile)

Max Activating Token Index: 463

Text #6

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1003507 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1928. Min Act: -0.0000

Data Index: 220364 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2171. Min Act: -0.0000

Data Index: 1211346 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1298101 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1731045 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1761. Min Act: -0.0000

Data Index: 705895 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2571. Min Act: -0.0000

Data Index: 444384 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2046. Min Act: -0.0000

Data Index: 409535 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.2783. Min Act: -0.0000

Data Index: 849771 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1680306 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1944. Min Act: -0.0000

Data Index: 1408598 (The Pile)

Max Activating Token Index: 286

Text #17

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1140. Min Act: -0.0000

Data Index: 475936 (The Pile)

Max Activating Token Index: 394

Text #18

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1821506 (The Pile)

Max Activating Token Index: 405

Text #19

Max Range: 1.4451. Min Range: -1.4451

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1029999 (The Pile)

Max Activating Token Index: 387