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

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

Neuron 5115 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1574535 (Python Code)

Max Activating Token Index: 954

Text #1

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1402182 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1381515 (Python Code)

Max Activating Token Index: 511

Text #3

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1590884 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1447109 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1492225 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1648203 (Python Code)

Max Activating Token Index: 724

Text #7

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1468203 (Python Code)

Max Activating Token Index: 142

Text #8

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1568162 (Python Code)

Max Activating Token Index: 781

Text #9

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4601. Min Act: -0.0000

Data Index: 1621999 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1462074 (Python Code)

Max Activating Token Index: 600

Text #11

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4242. Min Act: -0.0000

Data Index: 739189 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1590109 (Python Code)

Max Activating Token Index: 680

Text #13

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4050. Min Act: -0.0000

Data Index: 184858 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4268. Min Act: -0.0000

Data Index: 39203 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1216438 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1555988 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.3477. Min Act: -0.0000

Data Index: 104374 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1070172 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.9696. Min Range: -0.9696

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1315984 (C4 (Web Text))

Max Activating Token Index: 608