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

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

Neuron 3978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.5302. Min Act: -0.0000

Data Index: 469998 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.5056. Min Act: -0.0000

Data Index: 433030 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1049784 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.3453. Min Act: -0.0000

Data Index: 1016253 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.1504. Min Act: -0.0000

Data Index: 332185 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.1098. Min Act: -0.0000

Data Index: 917502 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0850. Min Act: -0.0000

Data Index: 647691 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1103186 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0635. Min Act: -0.0000

Data Index: 347899 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1205986 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0389. Min Act: -0.0000

Data Index: 559232 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0506. Min Act: -0.0000

Data Index: 632669 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0271. Min Act: -0.0000

Data Index: 825929 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.5302. Min Range: -1.5302

Max Act: 0.9730. Min Act: -0.0000

Data Index: 29077 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.5302. Min Range: -1.5302

Max Act: 0.9973. Min Act: -0.0000

Data Index: 173429 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 1.5302. Min Range: -1.5302

Max Act: 0.9991. Min Act: -0.0000

Data Index: 250644 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0209. Min Act: -0.0000

Data Index: 63281 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.5302. Min Range: -1.5302

Max Act: 1.0443. Min Act: -0.0000

Data Index: 134791 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 1.5302. Min Range: -1.5302

Max Act: 0.8850. Min Act: -0.0000

Data Index: 342949 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 1.5302. Min Range: -1.5302

Max Act: 0.9657. Min Act: -0.0000

Data Index: 104958 (C4 (Web Text))

Max Activating Token Index: 636