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

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

Neuron 3062 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1440607 (Python Code)

Max Activating Token Index: 365

Text #1

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8927. Min Act: -0.0000

Data Index: 360797 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8831. Min Act: -0.0000

Data Index: 977584 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1074816 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8449. Min Act: -0.0000

Data Index: 300712 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1561555 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1300678 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1403508 (Python Code)

Max Activating Token Index: 771

Text #8

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7752. Min Act: -0.0000

Data Index: 607090 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7487. Min Act: -0.0000

Data Index: 464510 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1126493 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7252. Min Act: -0.0000

Data Index: 683998 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1177847 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7185. Min Act: -0.0000

Data Index: 223986 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6651. Min Act: -0.0000

Data Index: 253218 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1059019 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6742. Min Act: -0.0000

Data Index: 285571 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6659. Min Act: -0.0000

Data Index: 55053 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6896. Min Act: -0.0000

Data Index: 889947 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.9679. Min Range: -0.9679

Max Act: 0.6832. Min Act: -0.0000

Data Index: 236131 (C4 (Web Text))

Max Activating Token Index: 802