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

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

Neuron 4489 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2403. Min Act: -0.0000

Data Index: 605975 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2478. Min Act: -0.0000

Data Index: 801837 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2236. Min Act: -0.0000

Data Index: 684091 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2200. Min Act: -0.0000

Data Index: 54404 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2293. Min Act: -0.0000

Data Index: 860860 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1010224 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2212. Min Act: -0.0000

Data Index: 482028 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2283. Min Act: -0.0000

Data Index: 838588 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2211. Min Act: -0.0000

Data Index: 47782 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2122. Min Act: -0.0000

Data Index: 441332 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2065. Min Act: -0.0000

Data Index: 457043 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2026. Min Act: -0.0000

Data Index: 631152 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2090. Min Act: -0.0000

Data Index: 304810 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2009. Min Act: -0.0000

Data Index: 152014 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1138921 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.2008. Min Act: -0.0000

Data Index: 199590 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1526. Min Act: -0.0000

Data Index: 305641 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1515. Min Act: -0.0000

Data Index: 432746 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1448. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.2478. Min Range: -0.2478

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 591