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

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

Neuron 4722 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.5300. Min Act: -0.0001

Data Index: 1176891 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.5087. Min Act: -0.0001

Data Index: 419621 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.4347. Min Act: -0.0000

Data Index: 590107 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.4406. Min Act: -0.0000

Data Index: 941618 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.4079. Min Act: -0.0000

Data Index: 676344 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.4225. Min Act: -0.0000

Data Index: 1298388 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.4183. Min Act: -0.0001

Data Index: 163896 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3894. Min Act: -0.0000

Data Index: 617141 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3932. Min Act: -0.0001

Data Index: 1142550 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3844. Min Act: -0.0001

Data Index: 692668 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3832. Min Act: -0.0001

Data Index: 383435 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3856. Min Act: -0.0001

Data Index: 1043026 (C4 (Web Text))

Max Activating Token Index: 405

Text #12

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3833. Min Act: -0.0001

Data Index: 981628 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3772. Min Act: -0.0001

Data Index: 801018 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3578. Min Act: -0.0001

Data Index: 1201518 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3577. Min Act: -0.0001

Data Index: 409788 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3535. Min Act: -0.0001

Data Index: 923739 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3583. Min Act: -0.0001

Data Index: 884790 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3447. Min Act: -0.0000

Data Index: 532626 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.5300. Min Range: -0.5300

Max Act: 0.3528. Min Act: -0.0001

Data Index: 1022733 (C4 (Web Text))

Max Activating Token Index: 786