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

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

Neuron 4461 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8789. Min Act: -0.0000

Data Index: 279157 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9382. Min Act: -0.0000

Data Index: 374964 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.9096. Min Act: -0.0000

Data Index: 920654 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8293. Min Act: -0.0000

Data Index: 650482 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8300. Min Act: -0.0000

Data Index: 884188 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8194. Min Act: -0.0000

Data Index: 648517 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8129. Min Act: -0.0000

Data Index: 386437 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8032. Min Act: -0.0000

Data Index: 712202 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7702. Min Act: -0.0000

Data Index: 780709 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7577. Min Act: -0.0000

Data Index: 461298 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7634. Min Act: -0.0000

Data Index: 808779 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7589. Min Act: -0.0000

Data Index: 507690 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7096. Min Act: -0.0000

Data Index: 545327 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7707. Min Act: -0.0000

Data Index: 780907 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7760. Min Act: -0.0000

Data Index: 521510 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1265542 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1314131 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7416. Min Act: -0.0000

Data Index: 722525 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7910. Min Act: -0.0001

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.9382. Min Range: -0.9382

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1078352 (C4 (Web Text))

Max Activating Token Index: 532