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

Dataset: The Pile

Neuron 1525 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1686. Min Act: -0.0000

Data Index: 1022175 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.9916. Min Act: -0.0000

Data Index: 539467 (The Pile)

Max Activating Token Index: 93

Text #2

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.4008. Min Act: -0.0000

Data Index: 1282666 (The Pile)

Max Activating Token Index: 229

Text #3

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0529. Min Act: -0.0000

Data Index: 430101 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.8955. Min Act: -0.0000

Data Index: 1939202 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1736. Min Act: -0.0000

Data Index: 1091064 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.8223. Min Act: -0.0000

Data Index: 980267 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.1056. Min Act: -0.0000

Data Index: 1871342 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.9859. Min Act: -0.0000

Data Index: 315566 (The Pile)

Max Activating Token Index: 608

Text #9

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.9594. Min Act: -0.0000

Data Index: 1350373 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.9100. Min Act: -0.0000

Data Index: 795504 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.7134. Min Act: -0.0000

Data Index: 593956 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0021. Min Act: -0.0000

Data Index: 1372859 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.6787. Min Act: -0.0000

Data Index: 449821 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.8345. Min Act: -0.0000

Data Index: 689344 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.9868. Min Act: -0.0000

Data Index: 1252582 (The Pile)

Max Activating Token Index: 669

Text #16

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.8171. Min Act: -0.0000

Data Index: 1492121 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.8026. Min Act: -0.0000

Data Index: 1274451 (The Pile)

Max Activating Token Index: 592

Text #18

Max Range: 3.4008. Min Range: -3.4008

Max Act: 2.9275. Min Act: -0.0000

Data Index: 445360 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 3.4008. Min Range: -3.4008

Max Act: 3.0739. Min Act: -0.0000

Data Index: 229544 (The Pile)

Max Activating Token Index: 300