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

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

Neuron 667 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.2249. Min Act: -0.0000

Data Index: 229559 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.2177. Min Act: -0.0000

Data Index: 589720 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.0323. Min Act: -0.0000

Data Index: 265204 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.0627. Min Act: -0.0000

Data Index: 291491 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.0346. Min Act: -0.0000

Data Index: 463266 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9859. Min Act: -0.0000

Data Index: 23063 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.2249. Min Range: -1.2249

Max Act: 1.0171. Min Act: -0.0000

Data Index: 632007 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9779. Min Act: -0.0000

Data Index: 686882 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9666. Min Act: -0.0000

Data Index: 431076 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1095623 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1099108 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9618. Min Act: -0.0000

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9736. Min Act: -0.0000

Data Index: 598072 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9724. Min Act: -0.0000

Data Index: 640564 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9593. Min Act: -0.0000

Data Index: 326159 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9564. Min Act: -0.0000

Data Index: 521070 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9504. Min Act: -0.0000

Data Index: 528171 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9517. Min Act: -0.0000

Data Index: 873254 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.9509. Min Act: -0.0000

Data Index: 489252 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 1.2249. Min Range: -1.2249

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1143994 (C4 (Web Text))

Max Activating Token Index: 710