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

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

Neuron 2512 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8744. Min Act: -0.0000

Data Index: 360375 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8452. Min Act: -0.0000

Data Index: 848259 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7523. Min Act: -0.0000

Data Index: 189318 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7271. Min Act: -0.0000

Data Index: 17907 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7021. Min Act: -0.0001

Data Index: 1108581 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6673. Min Act: -0.0001

Data Index: 627243 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7067. Min Act: -0.0000

Data Index: 250798 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1353941 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6419. Min Act: -0.0001

Data Index: 880642 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6325. Min Act: -0.0000

Data Index: 245898 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6668. Min Act: -0.0000

Data Index: 996915 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1352887 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1315953 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6018. Min Act: -0.0000

Data Index: 114889 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6407. Min Act: -0.0000

Data Index: 106278 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5292. Min Act: -0.0000

Data Index: 1314042 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1239882 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5559. Min Act: -0.0000

Data Index: 759415 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5363. Min Act: -0.0000

Data Index: 539410 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6155. Min Act: -0.0001

Data Index: 437576 (C4 (Web Text))

Max Activating Token Index: 702