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

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

Neuron 2468 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4876. Min Act: -0.0000

Data Index: 1442904 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1520747 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1489927 (Python Code)

Max Activating Token Index: 38

Text #3

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1398232 (Python Code)

Max Activating Token Index: 171

Text #4

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1409666 (Python Code)

Max Activating Token Index: 44

Text #5

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.4020. Min Act: -0.0000

Data Index: 1524966 (Python Code)

Max Activating Token Index: 207

Text #6

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1492240 (Python Code)

Max Activating Token Index: 324

Text #7

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1614266 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1446401 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1634398 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1575592 (Python Code)

Max Activating Token Index: 825

Text #11

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1417041 (Python Code)

Max Activating Token Index: 677

Text #12

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1400171 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1493405 (Python Code)

Max Activating Token Index: 66

Text #14

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1564727 (Python Code)

Max Activating Token Index: 393

Text #15

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1530228 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1396261 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1616274 (Python Code)

Max Activating Token Index: 259

Text #18

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1513833 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.4876. Min Range: -0.4876

Max Act: 0.3099. Min Act: -0.0000

Data Index: 1443530 (Python Code)

Max Activating Token Index: 234