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

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

Neuron 525 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.6340. Min Act: -0.0000

Data Index: 81881 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.6293. Min Act: 0.0000

Data Index: 133553 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1347149 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.6262. Min Act: -0.0000

Data Index: 833468 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5723. Min Act: -0.0000

Data Index: 969872 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1025931 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1156234 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5598. Min Act: -0.0000

Data Index: 387196 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5291. Min Act: 0.0000

Data Index: 716813 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5140. Min Act: 0.0000

Data Index: 616163 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5121. Min Act: -0.0000

Data Index: 956741 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5063. Min Act: -0.0000

Data Index: 764571 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5035. Min Act: 0.0000

Data Index: 167534 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5049. Min Act: -0.0000

Data Index: 11169 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1129270 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4821. Min Act: -0.0000

Data Index: 308880 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.5082. Min Act: -0.0000

Data Index: 586672 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4803. Min Act: -0.0000

Data Index: 945307 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1002343 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.6340. Min Range: -0.6340

Max Act: 0.4882. Min Act: -0.0000

Data Index: 208173 (C4 (Web Text))

Max Activating Token Index: 689