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

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

Neuron 3276 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.2059. Min Act: -0.0001

Data Index: 606638 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1935. Min Act: -0.0001

Data Index: 728490 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1878. Min Act: -0.0001

Data Index: 349970 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1223802 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1733. Min Act: -0.0001

Data Index: 124500 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1650. Min Act: -0.0001

Data Index: 262110 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1684. Min Act: -0.0001

Data Index: 904781 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1023657 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1712. Min Act: -0.0001

Data Index: 194818 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1593. Min Act: -0.0001

Data Index: 48953 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1645. Min Act: -0.0001

Data Index: 730222 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1245249 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1477. Min Act: -0.0001

Data Index: 914256 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1391. Min Act: -0.0001

Data Index: 135065 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1494. Min Act: -0.0001

Data Index: 771934 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1294227 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1406. Min Act: -0.0001

Data Index: 814938 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1154312 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1403. Min Act: -0.0001

Data Index: 415986 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.2059. Min Range: -0.2059

Max Act: 0.1321. Min Act: -0.0001

Data Index: 996230 (C4 (Web Text))

Max Activating Token Index: 16