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

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

Neuron 4599 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6721. Min Range: -2.6721

Max Act: 2.6721. Min Act: -0.0000

Data Index: 1295246 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 2.6721. Min Range: -2.6721

Max Act: 2.6297. Min Act: -0.0000

Data Index: 253106 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 2.6721. Min Range: -2.6721

Max Act: 2.6044. Min Act: -0.0000

Data Index: 1080704 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 2.6721. Min Range: -2.6721

Max Act: 2.2326. Min Act: -0.0000

Data Index: 102396 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 2.6721. Min Range: -2.6721

Max Act: 2.2135. Min Act: -0.0000

Data Index: 1231909 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 2.6721. Min Range: -2.6721

Max Act: 2.0592. Min Act: -0.0000

Data Index: 507750 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 2.6721. Min Range: -2.6721

Max Act: 2.0381. Min Act: -0.0000

Data Index: 307269 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.9409. Min Act: -0.0000

Data Index: 363247 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.8365. Min Act: -0.0000

Data Index: 1147851 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.9372. Min Act: -0.0000

Data Index: 1300816 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.9133. Min Act: -0.0000

Data Index: 315144 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.8802. Min Act: -0.0000

Data Index: 1061007 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.8704. Min Act: -0.0000

Data Index: 627255 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.8520. Min Act: -0.0000

Data Index: 605974 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.7486. Min Act: -0.0000

Data Index: 442284 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.7341. Min Act: -0.0000

Data Index: 1331399 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.7613. Min Act: -0.0000

Data Index: 459321 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.6291. Min Act: -0.0000

Data Index: 856857 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.7177. Min Act: -0.0000

Data Index: 477765 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 2.6721. Min Range: -2.6721

Max Act: 1.7119. Min Act: -0.0000

Data Index: 352807 (C4 (Web Text))

Max Activating Token Index: 492