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

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

Neuron 5680 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.4244. Min Act: -0.0000

Data Index: 960817 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.4023. Min Act: -0.0000

Data Index: 410609 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1038047 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1900. Min Act: -0.0000

Data Index: 339852 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1529. Min Act: -0.0000

Data Index: 163190 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1409. Min Act: -0.0000

Data Index: 704800 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1390. Min Act: -0.0000

Data Index: 465278 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.1721. Min Act: -0.0000

Data Index: 817564 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0696. Min Act: -0.0000

Data Index: 113853 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0342. Min Act: -0.0000

Data Index: 691165 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1151385 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 1.4244. Min Range: -1.4244

Max Act: 1.0274. Min Act: -0.0000

Data Index: 398420 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1011985 (C4 (Web Text))

Max Activating Token Index: 570

Text #13

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1066286 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9009. Min Act: -0.0000

Data Index: 1238142 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9495. Min Act: -0.0000

Data Index: 706753 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.8642. Min Act: -0.0000

Data Index: 97186 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9238. Min Act: -0.0000

Data Index: 462233 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9365. Min Act: -0.0000

Data Index: 665963 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 1.4244. Min Range: -1.4244

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1341318 (C4 (Web Text))

Max Activating Token Index: 361