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

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

Neuron 5439 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.1009. Min Act: -0.0000

Data Index: 108088 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0724. Min Act: -0.0000

Data Index: 458806 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1360701 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0750. Min Act: -0.0000

Data Index: 375026 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1556679 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0705. Min Act: -0.0000

Data Index: 437970 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1560081 (Python Code)

Max Activating Token Index: 662

Text #7

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1127618 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0599. Min Act: -0.0000

Data Index: 1591256 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1373125 (Python Code)

Max Activating Token Index: 310

Text #10

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1454404 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0561. Min Act: -0.0000

Data Index: 590186 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0565. Min Act: -0.0000

Data Index: 1611815 (Python Code)

Max Activating Token Index: 908

Text #13

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0580. Min Act: -0.0000

Data Index: 980008 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0579. Min Act: -0.0000

Data Index: 1620413 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1385117 (Python Code)

Max Activating Token Index: 756

Text #16

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0555. Min Act: -0.0000

Data Index: 1251367 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0570. Min Act: -0.0000

Data Index: 1540703 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0535. Min Act: -0.0000

Data Index: 840509 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0585. Min Act: -0.0000

Data Index: 968577 (C4 (Web Text))

Max Activating Token Index: 355