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

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

Neuron 3320 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.7662. Min Act: -0.0000

Data Index: 769258 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1165094 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.7098. Min Act: -0.0000

Data Index: 848704 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.7162. Min Act: -0.0001

Data Index: 989546 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6836. Min Act: -0.0000

Data Index: 800987 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.7044. Min Act: -0.0000

Data Index: 797091 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1191498 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6826. Min Act: -0.0000

Data Index: 435432 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6673. Min Act: -0.0000

Data Index: 164382 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6770. Min Act: -0.0000

Data Index: 869355 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6404. Min Act: -0.0000

Data Index: 798538 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6411. Min Act: -0.0000

Data Index: 143622 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1081654 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6519. Min Act: -0.0000

Data Index: 252564 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6515. Min Act: -0.0000

Data Index: 210998 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6359. Min Act: -0.0000

Data Index: 238272 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1280287 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1170226 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6459. Min Act: -0.0000

Data Index: 827343 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 0.7662. Min Range: -0.7662

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1280806 (C4 (Web Text))

Max Activating Token Index: 398