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

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

Neuron 4479 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.8611. Min Act: -0.0000

Data Index: 160010 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.5305. Min Act: -0.0000

Data Index: 202682 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.6467. Min Act: -0.0000

Data Index: 310193 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.6190. Min Act: -0.0000

Data Index: 724020 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.7607. Min Act: -0.0000

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.5383. Min Act: -0.0000

Data Index: 527891 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.5378. Min Act: -0.0000

Data Index: 550965 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.5231. Min Act: -0.0000

Data Index: 165515 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.6576. Min Act: -0.0000

Data Index: 1184196 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.5100. Min Act: -0.0000

Data Index: 848288 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.3730. Min Act: -0.0000

Data Index: 752426 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.4508. Min Act: -0.0000

Data Index: 100666 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.4567. Min Act: -0.0000

Data Index: 935596 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.3226. Min Act: -0.0000

Data Index: 838138 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.4408. Min Act: -0.0000

Data Index: 1101137 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.5626. Min Act: -0.0000

Data Index: 1301738 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.3761. Min Act: -0.0000

Data Index: 560982 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.4199. Min Act: -0.0000

Data Index: 876732 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.4070. Min Act: -0.0000

Data Index: 1230481 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 2.8611. Min Range: -2.8611

Max Act: 2.5478. Min Act: -0.0000

Data Index: 1354497 (C4 (Web Text))

Max Activating Token Index: 1011