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

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

Neuron 4488 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.5345. Min Act: -0.0000

Data Index: 489733 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.4046. Min Act: -0.0000

Data Index: 1057358 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.5345. Min Range: -1.5345

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1251101 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.9501. Min Act: -0.0000

Data Index: 153218 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8872. Min Act: -0.0000

Data Index: 779622 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8781. Min Act: -0.0000

Data Index: 679997 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8521. Min Act: -0.0000

Data Index: 660520 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8418. Min Act: -0.0000

Data Index: 624933 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8361. Min Act: -0.0000

Data Index: 60274 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1050107 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8293. Min Act: -0.0000

Data Index: 162448 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8023. Min Act: -0.0000

Data Index: 738030 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1077886 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.7432. Min Act: -0.0000

Data Index: 741786 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.7825. Min Act: -0.0000

Data Index: 584269 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.7118. Min Act: -0.0000

Data Index: 619012 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1225995 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.7025. Min Act: -0.0000

Data Index: 86896 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.7032. Min Act: -0.0000

Data Index: 960384 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.5345. Min Range: -1.5345

Max Act: 0.7962. Min Act: -0.0000

Data Index: 935617 (C4 (Web Text))

Max Activating Token Index: 353