Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3152 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0787. Min Act: -0.0000

Data Index: 830885 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0807. Min Act: -0.0000

Data Index: 186848 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1334530 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0735. Min Act: -0.0000

Data Index: 513306 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0733. Min Act: -0.0000

Data Index: 780937 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1002603 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0659. Min Act: -0.0000

Data Index: 316630 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0571. Min Act: -0.0000

Data Index: 85272 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0550. Min Act: -0.0000

Data Index: 402290 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0628. Min Act: -0.0000

Data Index: 224189 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0587. Min Act: -0.0000

Data Index: 641945 (C4 (Web Text))

Max Activating Token Index: 376

Text #11

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0622. Min Act: -0.0001

Data Index: 539102 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0577. Min Act: -0.0000

Data Index: 363308 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0573. Min Act: -0.0000

Data Index: 464636 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0609. Min Act: -0.0000

Data Index: 375950 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0590. Min Act: -0.0000

Data Index: 997640 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0564. Min Act: -0.0000

Data Index: 193240 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0519. Min Act: -0.0000

Data Index: 497054 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0555. Min Act: -0.0000

Data Index: 470484 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0807. Min Range: -0.0807

Max Act: 0.0555. Min Act: -0.0001

Data Index: 571797 (C4 (Web Text))

Max Activating Token Index: 284