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

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

Neuron 4256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1313. Min Act: -0.0000

Data Index: 183694 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1556469 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1163. Min Act: -0.0000

Data Index: 1490502 (Python Code)

Max Activating Token Index: 215

Text #3

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1232. Min Act: -0.0000

Data Index: 849314 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1256178 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1097210 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1045. Min Act: -0.0000

Data Index: 24825 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1015. Min Act: -0.0000

Data Index: 415135 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0930. Min Act: -0.0000

Data Index: 13169 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1436472 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1460063 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1561770 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1643560 (Python Code)

Max Activating Token Index: 1002

Text #13

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1412439 (Python Code)

Max Activating Token Index: 631

Text #14

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0970. Min Act: -0.0000

Data Index: 1484878 (Python Code)

Max Activating Token Index: 395

Text #15

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1618571 (Python Code)

Max Activating Token Index: 722

Text #16

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0963. Min Act: -0.0000

Data Index: 690165 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1425648 (Python Code)

Max Activating Token Index: 784

Text #18

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1486593 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.1313. Min Range: -0.1313

Max Act: 0.0977. Min Act: -0.0000

Data Index: 448836 (C4 (Web Text))

Max Activating Token Index: 341