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

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

Neuron 5085 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4482. Min Range: -1.4482

Max Act: 1.4482. Min Act: -0.0000

Data Index: 7119 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.9458. Min Act: -0.0000

Data Index: 878559 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.8222. Min Act: -0.0000

Data Index: 618475 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6568. Min Act: -0.0000

Data Index: 295353 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6935. Min Act: -0.0000

Data Index: 173462 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6120. Min Act: -0.0000

Data Index: 807832 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1149177 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1151323 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1101201 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6216. Min Act: -0.0000

Data Index: 965135 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1314716 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5686. Min Act: -0.0000

Data Index: 702714 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5843. Min Act: -0.0000

Data Index: 348006 (C4 (Web Text))

Max Activating Token Index: 110

Text #13

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5679. Min Act: -0.0000

Data Index: 623394 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6184. Min Act: -0.0000

Data Index: 473950 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5948. Min Act: -0.0000

Data Index: 697964 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1357910 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5989. Min Act: -0.0000

Data Index: 169665 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1335865 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 1.4482. Min Range: -1.4482

Max Act: 0.5671. Min Act: -0.0000

Data Index: 840200 (C4 (Web Text))

Max Activating Token Index: 658