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

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

Neuron 1550 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.1508. Min Act: -0.0000

Data Index: 726491 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.9499. Min Act: -0.0000

Data Index: 532316 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8636. Min Act: -0.0000

Data Index: 193129 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8871. Min Act: -0.0000

Data Index: 500482 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.9674. Min Act: -0.0000

Data Index: 38006 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.9536. Min Act: -0.0000

Data Index: 1037036 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7070. Min Act: -0.0000

Data Index: 1127512 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8143. Min Act: -0.0000

Data Index: 377575 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7033. Min Act: -0.0000

Data Index: 227832 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.6913. Min Act: -0.0000

Data Index: 298444 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5363. Min Act: -0.0000

Data Index: 638349 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.6827. Min Act: -0.0000

Data Index: 1049688 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4933. Min Act: -0.0000

Data Index: 557514 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.6610. Min Act: -0.0000

Data Index: 1305883 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1334833 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1118582 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.4648. Min Act: -0.0000

Data Index: 43934 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5324. Min Act: -0.0000

Data Index: 265615 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5966. Min Act: -0.0000

Data Index: 106335 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.5546. Min Act: -0.0000

Data Index: 225245 (C4 (Web Text))

Max Activating Token Index: 889