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

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

Neuron 1906 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1041710 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3602. Min Act: -0.0000

Data Index: 959897 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3489. Min Act: -0.0000

Data Index: 439709 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3254. Min Act: -0.0000

Data Index: 276297 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2897. Min Act: -0.0000

Data Index: 83005 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1049784 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2726. Min Act: -0.0000

Data Index: 706092 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2798. Min Act: -0.0000

Data Index: 338449 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2590. Min Act: -0.0000

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2680. Min Act: -0.0000

Data Index: 664021 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2741. Min Act: -0.0000

Data Index: 786532 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2838. Min Act: -0.0000

Data Index: 921276 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2718. Min Act: -0.0000

Data Index: 601940 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2634. Min Act: -0.0000

Data Index: 648371 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1192365 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2693. Min Act: -0.0000

Data Index: 963143 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2564. Min Act: -0.0000

Data Index: 684001 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2544. Min Act: -0.0000

Data Index: 858953 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2399. Min Act: -0.0000

Data Index: 1274222 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2348. Min Act: -0.0000

Data Index: 746397 (C4 (Web Text))

Max Activating Token Index: 692