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

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

Neuron 3350 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: 1.8606. Min Range: -1.8606

Max Act: 1.8606. Min Act: -0.0000

Data Index: 568393 (C4 (Web Text))

Max Activating Token Index: 834

Text #1

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.7029. Min Act: -0.0000

Data Index: 1160113 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6864. Min Act: -0.0000

Data Index: 1306411 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.7582. Min Act: -0.0000

Data Index: 224627 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.8388. Min Act: -0.0000

Data Index: 1324549 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6333. Min Act: -0.0000

Data Index: 246422 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6248. Min Act: -0.0000

Data Index: 287189 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6814. Min Act: -0.0000

Data Index: 43430 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6868. Min Act: -0.0000

Data Index: 974527 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6737. Min Act: -0.0000

Data Index: 229605 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5358. Min Act: -0.0000

Data Index: 795195 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6113. Min Act: -0.0000

Data Index: 950289 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6045. Min Act: -0.0000

Data Index: 972498 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.6179. Min Act: -0.0000

Data Index: 927962 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5186. Min Act: -0.0000

Data Index: 839568 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5076. Min Act: -0.0000

Data Index: 1109672 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.7474. Min Act: -0.0000

Data Index: 1181538 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4678. Min Act: -0.0001

Data Index: 1208175 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.4901. Min Act: -0.0000

Data Index: 431788 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 1.8606. Min Range: -1.8606

Max Act: 1.5229. Min Act: -0.0000

Data Index: 659391 (C4 (Web Text))

Max Activating Token Index: 891