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

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

Neuron 3372 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: 8.0345. Min Range: -8.0345

Max Act: 8.0345. Min Act: -0.0000

Data Index: 1589735 (Python Code)

Max Activating Token Index: 878

Text #1

Max Range: 8.0345. Min Range: -8.0345

Max Act: 7.1004. Min Act: -0.0000

Data Index: 1370175 (Python Code)

Max Activating Token Index: 124

Text #2

Max Range: 8.0345. Min Range: -8.0345

Max Act: 7.4172. Min Act: -0.0000

Data Index: 1564348 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 8.0345. Min Range: -8.0345

Max Act: 7.1979. Min Act: -0.0000

Data Index: 1501046 (Python Code)

Max Activating Token Index: 237

Text #4

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.9139. Min Act: -0.0000

Data Index: 1375853 (Python Code)

Max Activating Token Index: 344

Text #5

Max Range: 8.0345. Min Range: -8.0345

Max Act: 7.1124. Min Act: -0.0000

Data Index: 1583447 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 8.0345. Min Range: -8.0345

Max Act: 7.0432. Min Act: -0.0000

Data Index: 1488799 (Python Code)

Max Activating Token Index: 406

Text #7

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.8540. Min Act: -0.0000

Data Index: 1436233 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.5863. Min Act: -0.0000

Data Index: 1573189 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.5269. Min Act: -0.0000

Data Index: 1584588 (Python Code)

Max Activating Token Index: 224

Text #10

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.4385. Min Act: -0.0000

Data Index: 1383665 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.7484. Min Act: -0.0000

Data Index: 1424923 (Python Code)

Max Activating Token Index: 427

Text #12

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.7208. Min Act: -0.0000

Data Index: 1369247 (Python Code)

Max Activating Token Index: 215

Text #13

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.3415. Min Act: -0.0000

Data Index: 1602009 (Python Code)

Max Activating Token Index: 171

Text #14

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.6239. Min Act: -0.0000

Data Index: 1454817 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.4364. Min Act: -0.0000

Data Index: 1489416 (Python Code)

Max Activating Token Index: 692

Text #16

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.7416. Min Act: -0.0000

Data Index: 1628103 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.7541. Min Act: -0.0000

Data Index: 1377762 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.5145. Min Act: -0.0000

Data Index: 1440819 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 8.0345. Min Range: -8.0345

Max Act: 6.2753. Min Act: -0.0000

Data Index: 1566107 (Python Code)

Max Activating Token Index: 94