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

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

Neuron 1509 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: 1.3884. Min Range: -1.3884

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1363392 (Python Code)

Max Activating Token Index: 350

Text #1

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.3117. Min Act: -0.0000

Data Index: 1468605 (Python Code)

Max Activating Token Index: 360

Text #2

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1589119 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2114. Min Act: -0.0000

Data Index: 1607729 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1624723 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1504722 (Python Code)

Max Activating Token Index: 509

Text #6

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1362677 (Python Code)

Max Activating Token Index: 180

Text #7

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1628036 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1539373 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1380490 (Python Code)

Max Activating Token Index: 364

Text #10

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0704. Min Act: -0.0000

Data Index: 1544639 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1521485 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1505163 (Python Code)

Max Activating Token Index: 701

Text #13

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1655783 (Python Code)

Max Activating Token Index: 161

Text #14

Max Range: 1.3884. Min Range: -1.3884

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1391269 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1648300 (Python Code)

Max Activating Token Index: 88

Text #16

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1451635 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1589335 (Python Code)

Max Activating Token Index: 194

Text #18

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1624755 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 1.3884. Min Range: -1.3884

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1498575 (Python Code)

Max Activating Token Index: 138