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

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

Neuron 446 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8612. Min Act: -0.0000

Data Index: 200503 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8846. Min Act: -0.0000

Data Index: 22968 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8591. Min Act: -0.0000

Data Index: 290986 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7411. Min Act: -0.0000

Data Index: 862238 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7982. Min Act: -0.0000

Data Index: 440256 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8550. Min Act: -0.0000

Data Index: 758773 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8538. Min Act: -0.0000

Data Index: 841505 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8744. Min Act: -0.0000

Data Index: 677465 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1041650 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7802. Min Act: -0.0000

Data Index: 409139 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6720. Min Act: -0.0000

Data Index: 157072 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7619. Min Act: -0.0000

Data Index: 6309 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7504. Min Act: -0.0000

Data Index: 246513 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7478. Min Act: -0.0001

Data Index: 1213586 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6703. Min Act: -0.0001

Data Index: 1315178 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6510. Min Act: -0.0001

Data Index: 902465 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7701. Min Act: -0.0000

Data Index: 293697 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7232. Min Act: -0.0000

Data Index: 191250 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.7073. Min Act: -0.0000

Data Index: 107769 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.8846. Min Range: -0.8846

Max Act: 0.6670. Min Act: -0.0000

Data Index: 606006 (C4 (Web Text))

Max Activating Token Index: 226