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

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

Neuron 334 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.4320. Min Act: -0.0001

Data Index: 721435 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3340. Min Act: -0.0001

Data Index: 409399 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.3241. Min Act: -0.0001

Data Index: 561502 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.4250. Min Act: -0.0001

Data Index: 1352035 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1684. Min Act: -0.0001

Data Index: 240589 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1649. Min Act: -0.0001

Data Index: 1348069 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1110. Min Act: -0.0001

Data Index: 917586 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0650. Min Act: -0.0001

Data Index: 952275 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0899. Min Act: -0.0001

Data Index: 683200 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1486. Min Act: -0.0001

Data Index: 331700 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1930. Min Act: -0.0001

Data Index: 191722 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1813. Min Act: -0.0000

Data Index: 158968 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0705. Min Act: -0.0001

Data Index: 1127827 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0447. Min Act: -0.0001

Data Index: 598634 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.1026. Min Act: -0.0000

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0357. Min Act: -0.0001

Data Index: 497299 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0614. Min Act: -0.0001

Data Index: 500665 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1143917 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 1.4320. Min Range: -1.4320

Max Act: 0.9555. Min Act: -0.0001

Data Index: 324573 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.4320. Min Range: -1.4320

Max Act: 1.0307. Min Act: -0.0001

Data Index: 1036051 (C4 (Web Text))

Max Activating Token Index: 450