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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2597 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3436. Min Act: -0.0002

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.3313. Min Act: -0.0003

Data Index: 829060 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2945. Min Act: -0.0002

Data Index: 454510 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2404. Min Act: -0.0003

Data Index: 528672 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2151. Min Act: -0.0003

Data Index: 472584 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2180. Min Act: -0.0003

Data Index: 399337 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2114. Min Act: -0.0002

Data Index: 709040 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2102. Min Act: -0.0003

Data Index: 1179832 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2083. Min Act: -0.0003

Data Index: 1074047 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2047. Min Act: -0.0003

Data Index: 1015373 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2038. Min Act: -0.0003

Data Index: 50687 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.2015. Min Act: -0.0003

Data Index: 865084 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1997. Min Act: -0.0003

Data Index: 1265737 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1982. Min Act: -0.0003

Data Index: 738920 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1907. Min Act: -0.0002

Data Index: 576407 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1975. Min Act: -0.0003

Data Index: 1171790 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1971. Min Act: -0.0003

Data Index: 989240 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1974. Min Act: -0.0003

Data Index: 146477 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1930. Min Act: -0.0003

Data Index: 390273 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.3436. Min Range: -0.3436

Max Act: 0.1905. Min Act: -0.0003

Data Index: 856627 (C4 (Web Text))

Max Activating Token Index: 454