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

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

Neuron 4337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.8397. Min Act: -0.0000

Data Index: 696301 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6746. Min Act: -0.0000

Data Index: 694773 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6795. Min Act: -0.0000

Data Index: 157166 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6535. Min Act: -0.0000

Data Index: 927537 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6397. Min Act: -0.0000

Data Index: 203556 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6394. Min Act: -0.0000

Data Index: 681969 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6711. Min Act: -0.0000

Data Index: 424900 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1305861 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1111871 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6224. Min Act: -0.0000

Data Index: 244267 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1216212 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6272. Min Act: -0.0000

Data Index: 468601 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5796. Min Act: -0.0000

Data Index: 539597 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6159. Min Act: -0.0000

Data Index: 874981 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1206317 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6066. Min Act: -0.0000

Data Index: 323437 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1134715 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.6077. Min Act: -0.0000

Data Index: 63819 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5472. Min Act: -0.0000

Data Index: 692140 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.8397. Min Range: -0.8397

Max Act: 0.5718. Min Act: -0.0000

Data Index: 506300 (C4 (Web Text))

Max Activating Token Index: 868