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

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

Neuron 3518 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.6838. Min Act: -0.0000

Data Index: 1206617 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1302679 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.2746. Min Act: -0.0000

Data Index: 1107128 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1026419 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.2750. Min Act: -0.0000

Data Index: 951708 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.1730. Min Act: -0.0000

Data Index: 669782 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.2028. Min Act: -0.0000

Data Index: 171515 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1162218 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.0975. Min Act: -0.0000

Data Index: 820948 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.1666. Min Act: -0.0000

Data Index: 750929 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1310117 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.1359. Min Act: -0.0000

Data Index: 1200122 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.6838. Min Range: -1.6838

Max Act: 0.9546. Min Act: -0.0000

Data Index: 868082 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.0542. Min Act: -0.0000

Data Index: 7097 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.0021. Min Act: -0.0000

Data Index: 96269 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.6838. Min Range: -1.6838

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1009996 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.6838. Min Range: -1.6838

Max Act: 1.0262. Min Act: -0.0000

Data Index: 658050 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.6838. Min Range: -1.6838

Max Act: 0.8470. Min Act: -0.0000

Data Index: 787858 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 1.6838. Min Range: -1.6838

Max Act: 0.8429. Min Act: -0.0000

Data Index: 875850 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.6838. Min Range: -1.6838

Max Act: 0.7547. Min Act: -0.0000

Data Index: 95260 (C4 (Web Text))

Max Activating Token Index: 341