Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4783 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.7264. Min Act: -0.0000

Data Index: 1461542 (Python Code)

Max Activating Token Index: 606

Text #1

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.6447. Min Act: -0.0000

Data Index: 1410220 (Python Code)

Max Activating Token Index: 999

Text #2

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5232. Min Act: -0.0000

Data Index: 1440486 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1401072 (Python Code)

Max Activating Token Index: 928

Text #4

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5833. Min Act: -0.0000

Data Index: 1632750 (Python Code)

Max Activating Token Index: 255

Text #5

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.6111. Min Act: -0.0000

Data Index: 1604396 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1535726 (Python Code)

Max Activating Token Index: 936

Text #7

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1463250 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5497. Min Act: -0.0000

Data Index: 1485720 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4522. Min Act: -0.0000

Data Index: 1567761 (Python Code)

Max Activating Token Index: 986

Text #10

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4899. Min Act: -0.0000

Data Index: 1410363 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1461230 (Python Code)

Max Activating Token Index: 950

Text #12

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4368. Min Act: -0.0000

Data Index: 1399122 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3841. Min Act: -0.0000

Data Index: 1553593 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.3909. Min Act: -0.0000

Data Index: 1457158 (Python Code)

Max Activating Token Index: 792

Text #15

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4541. Min Act: -0.0000

Data Index: 1367059 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1535303 (Python Code)

Max Activating Token Index: 151

Text #17

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1522708 (Python Code)

Max Activating Token Index: 263

Text #18

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1609292 (Python Code)

Max Activating Token Index: 672

Text #19

Max Range: 1.7264. Min Range: -1.7264

Max Act: 1.4484. Min Act: -0.0000

Data Index: 1624584 (Python Code)

Max Activating Token Index: 835