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

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

Neuron 4892 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1593375 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.1873. Min Act: -0.0000

Data Index: 241904 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0857. Min Act: -0.0000

Data Index: 447756 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1173882 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9634. Min Act: -0.0000

Data Index: 1354740 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1067450 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.3559. Min Range: -1.3559

Max Act: 1.0320. Min Act: -0.0000

Data Index: 853956 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1174285 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9442. Min Act: -0.0000

Data Index: 993960 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9546. Min Act: -0.0000

Data Index: 798434 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8907. Min Act: -0.0000

Data Index: 78463 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8916. Min Act: -0.0000

Data Index: 406976 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8829. Min Act: -0.0000

Data Index: 67269 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1262081 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8090. Min Act: -0.0000

Data Index: 818278 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8459. Min Act: -0.0000

Data Index: 73687 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8833. Min Act: -0.0000

Data Index: 803877 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.8192. Min Act: -0.0000

Data Index: 203026 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.9260. Min Act: -0.0000

Data Index: 51300 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 1.3559. Min Range: -1.3559

Max Act: 0.7645. Min Act: -0.0000

Data Index: 888220 (C4 (Web Text))

Max Activating Token Index: 351