Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 599 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0003

Data Index: 158571 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1171137 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1154016 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0262. Min Act: -0.0003

Data Index: 331436 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0251. Min Act: -0.0003

Data Index: 782370 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0261. Min Act: -0.0004

Data Index: 316106 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1081766 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1495570 (Python Code)

Max Activating Token Index: 982

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0257. Min Act: -0.0002

Data Index: 317804 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1526564 (Python Code)

Max Activating Token Index: 321

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0262. Min Act: -0.0002

Data Index: 656672 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1455246 (Python Code)

Max Activating Token Index: 180

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1152147 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1097983 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0250. Min Act: -0.0003

Data Index: 196873 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1452428 (Python Code)

Max Activating Token Index: 578

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1378789 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0246. Min Act: -0.0004

Data Index: 709158 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1419927 (Python Code)

Max Activating Token Index: 357

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0244. Min Act: -0.0004

Data Index: 383743 (C4 (Web Text))

Max Activating Token Index: 271