Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 775 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1379. Min Range: -3.1379

Max Act: 3.1379. Min Act: -0.0001

Data Index: 863731 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.8902. Min Act: -0.0001

Data Index: 686520 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.8845. Min Act: -0.0001

Data Index: 51140 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 3.1379. Min Range: -3.1379

Max Act: 3.0161. Min Act: -0.0001

Data Index: 439504 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 3.1379. Min Range: -3.1379

Max Act: 3.0123. Min Act: -0.0001

Data Index: 1356585 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 3.1379. Min Range: -3.1379

Max Act: 3.0242. Min Act: -0.0001

Data Index: 636145 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 3.1379. Min Range: -3.1379

Max Act: 3.0043. Min Act: -0.0001

Data Index: 847349 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.9570. Min Act: -0.0001

Data Index: 905392 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.9201. Min Act: -0.0001

Data Index: 436464 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.9308. Min Act: -0.0001

Data Index: 608764 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.9087. Min Act: -0.0001

Data Index: 621876 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.9266. Min Act: -0.0001

Data Index: 1301868 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.8955. Min Act: -0.0001

Data Index: 13710 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.9128. Min Act: -0.0000

Data Index: 660730 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.8914. Min Act: -0.0001

Data Index: 813863 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.8776. Min Act: -0.0001

Data Index: 836123 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.8803. Min Act: -0.0001

Data Index: 1137546 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.8628. Min Act: -0.0001

Data Index: 1253107 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.7653. Min Act: -0.0001

Data Index: 107232 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 3.1379. Min Range: -3.1379

Max Act: 2.7522. Min Act: -0.0001

Data Index: 655828 (C4 (Web Text))

Max Activating Token Index: 651