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

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

Neuron 4145 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5496. Min Range: -1.5496

Max Act: 1.5496. Min Act: -0.0000

Data Index: 323281 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 1.5496. Min Range: -1.5496

Max Act: 1.4058. Min Act: -0.0000

Data Index: 736548 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.5496. Min Range: -1.5496

Max Act: 1.0265. Min Act: -0.0000

Data Index: 205842 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1213798 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.8223. Min Act: -0.0000

Data Index: 778490 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.8656. Min Act: -0.0000

Data Index: 896901 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7761. Min Act: -0.0000

Data Index: 685149 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7567. Min Act: -0.0000

Data Index: 135062 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7504. Min Act: -0.0000

Data Index: 69657 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1191632 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7464. Min Act: -0.0000

Data Index: 622991 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7642. Min Act: -0.0000

Data Index: 56951 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1154383 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7236. Min Act: -0.0000

Data Index: 753597 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7801. Min Act: -0.0000

Data Index: 689663 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7043. Min Act: -0.0000

Data Index: 273690 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7256. Min Act: -0.0000

Data Index: 763099 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7032. Min Act: -0.0000

Data Index: 640152 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.8172. Min Act: -0.0000

Data Index: 726377 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.5496. Min Range: -1.5496

Max Act: 0.7233. Min Act: -0.0000

Data Index: 362996 (C4 (Web Text))

Max Activating Token Index: 977