Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 442 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4856. Min Act: -0.0000

Data Index: 73750 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4493. Min Act: -0.0000

Data Index: 854842 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4622. Min Act: -0.0000

Data Index: 918283 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1035402 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4315. Min Act: -0.0000

Data Index: 777319 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4288. Min Act: -0.0000

Data Index: 221772 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4346. Min Act: -0.0000

Data Index: 320347 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.4031. Min Act: -0.0000

Data Index: 1228703 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1420019 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3578. Min Act: -0.0000

Data Index: 543112 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3891. Min Act: -0.0000

Data Index: 1318781 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3612. Min Act: -0.0000

Data Index: 186510 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3616. Min Act: -0.0000

Data Index: 1025677 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3827. Min Act: -0.0000

Data Index: 921478 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1260188 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1487131 (Python Code)

Max Activating Token Index: 891

Text #16

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3736. Min Act: -0.0000

Data Index: 377954 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1374917 (Python Code)

Max Activating Token Index: 931

Text #18

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1519138 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 0.4856. Min Range: -0.4856

Max Act: 0.3676. Min Act: -0.0000

Data Index: 509074 (C4 (Web Text))

Max Activating Token Index: 473