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

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

Neuron 1237 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.9264. Min Act: -0.0001

Data Index: 1481694 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1493933 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.6800. Min Act: -0.0001

Data Index: 1412878 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4864. Min Act: -0.0001

Data Index: 1557179 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4038. Min Act: -0.0001

Data Index: 1503825 (Python Code)

Max Activating Token Index: 188

Text #5

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.5835. Min Act: -0.0001

Data Index: 1620888 (Python Code)

Max Activating Token Index: 787

Text #6

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.5270. Min Act: -0.0001

Data Index: 1478223 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.5155. Min Act: -0.0001

Data Index: 1536658 (Python Code)

Max Activating Token Index: 551

Text #8

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4566. Min Act: -0.0001

Data Index: 1415574 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4976. Min Act: -0.0001

Data Index: 1652380 (Python Code)

Max Activating Token Index: 474

Text #10

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4023. Min Act: -0.0001

Data Index: 1566817 (Python Code)

Max Activating Token Index: 685

Text #11

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.3761. Min Act: -0.0001

Data Index: 1564730 (Python Code)

Max Activating Token Index: 266

Text #12

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.3710. Min Act: -0.0001

Data Index: 1437361 (Python Code)

Max Activating Token Index: 544

Text #13

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4216. Min Act: -0.0001

Data Index: 1594212 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.3374. Min Act: -0.0001

Data Index: 1642488 (Python Code)

Max Activating Token Index: 596

Text #15

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.3792. Min Act: -0.0001

Data Index: 1641446 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.2422. Min Act: -0.0001

Data Index: 1643843 (Python Code)

Max Activating Token Index: 820

Text #17

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.4316. Min Act: -0.0001

Data Index: 1384679 (Python Code)

Max Activating Token Index: 45

Text #18

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.3171. Min Act: -0.0001

Data Index: 1473481 (Python Code)

Max Activating Token Index: 918

Text #19

Max Range: 1.9264. Min Range: -1.9264

Max Act: 1.3648. Min Act: -0.0001

Data Index: 1400136 (Python Code)

Max Activating Token Index: 29