Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2357 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4822. Min Act: -0.0000

Data Index: 200112 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1449392 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1589478 (Python Code)

Max Activating Token Index: 99

Text #3

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4231. Min Act: -0.0000

Data Index: 811929 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3972. Min Act: -0.0000

Data Index: 103465 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1280280 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3981. Min Act: -0.0000

Data Index: 1448706 (Python Code)

Max Activating Token Index: 238

Text #7

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.4061. Min Act: -0.0000

Data Index: 169893 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3994. Min Act: -0.0000

Data Index: 904606 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3990. Min Act: -0.0000

Data Index: 93692 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3699. Min Act: -0.0000

Data Index: 580316 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3970. Min Act: -0.0000

Data Index: 258277 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3705. Min Act: -0.0000

Data Index: 87267 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1184513 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3546. Min Act: -0.0000

Data Index: 862477 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1178862 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1574637 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1076772 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3411. Min Act: -0.0000

Data Index: 984196 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.4822. Min Range: -0.4822

Max Act: 0.3476. Min Act: -0.0000

Data Index: 609485 (C4 (Web Text))

Max Activating Token Index: 42