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

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

Neuron 210 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2281. Min Range: -1.2281

Max Act: 1.2281. Min Act: -0.0001

Data Index: 241955 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 1.2281. Min Range: -1.2281

Max Act: 1.2194. Min Act: -0.0001

Data Index: 328789 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.9094. Min Act: -0.0001

Data Index: 357007 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8789. Min Act: -0.0001

Data Index: 573100 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8750. Min Act: -0.0001

Data Index: 647546 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8425. Min Act: -0.0001

Data Index: 1346800 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8403. Min Act: -0.0001

Data Index: 861377 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8261. Min Act: -0.0001

Data Index: 799691 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.7780. Min Act: -0.0001

Data Index: 640005 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8038. Min Act: -0.0001

Data Index: 409156 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8292. Min Act: -0.0001

Data Index: 13412 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1199184 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.7665. Min Act: -0.0001

Data Index: 1172054 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.7995. Min Act: -0.0001

Data Index: 387583 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8876. Min Act: -0.0001

Data Index: 439743 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.7301. Min Act: -0.0001

Data Index: 588430 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8483. Min Act: -0.0001

Data Index: 789974 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.8620. Min Act: -0.0001

Data Index: 1170134 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.6648. Min Act: -0.0001

Data Index: 1225015 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.2281. Min Range: -1.2281

Max Act: 0.7254. Min Act: -0.0001

Data Index: 688946 (C4 (Web Text))

Max Activating Token Index: 192