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

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

Neuron 3687 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: 2.8854. Min Range: -2.8854

Max Act: 2.8854. Min Act: -0.0000

Data Index: 1488783 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.5208. Min Act: -0.0000

Data Index: 1619033 (Python Code)

Max Activating Token Index: 248

Text #2

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.4812. Min Act: -0.0000

Data Index: 1421006 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.3052. Min Act: -0.0001

Data Index: 1636308 (Python Code)

Max Activating Token Index: 374

Text #4

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.4484. Min Act: -0.0001

Data Index: 1649121 (Python Code)

Max Activating Token Index: 314

Text #5

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.4158. Min Act: -0.0000

Data Index: 1566813 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.2743. Min Act: -0.0001

Data Index: 1360234 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.3834. Min Act: -0.0001

Data Index: 1533285 (Python Code)

Max Activating Token Index: 578

Text #8

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.3656. Min Act: -0.0000

Data Index: 1485190 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.3435. Min Act: -0.0001

Data Index: 1432127 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.2941. Min Act: -0.0000

Data Index: 1423759 (Python Code)

Max Activating Token Index: 622

Text #11

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.2131. Min Act: -0.0000

Data Index: 1653357 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.3310. Min Act: -0.0000

Data Index: 1577433 (Python Code)

Max Activating Token Index: 449

Text #13

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.4664. Min Act: -0.0000

Data Index: 1603314 (Python Code)

Max Activating Token Index: 643

Text #14

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.2719. Min Act: -0.0000

Data Index: 1413196 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.3914. Min Act: -0.0001

Data Index: 1375094 (Python Code)

Max Activating Token Index: 594

Text #16

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.1410. Min Act: -0.0000

Data Index: 1511281 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.3242. Min Act: -0.0001

Data Index: 1543325 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.1268. Min Act: -0.0000

Data Index: 1570245 (Python Code)

Max Activating Token Index: 1015

Text #19

Max Range: 2.8854. Min Range: -2.8854

Max Act: 2.1710. Min Act: -0.0000

Data Index: 1534774 (Python Code)

Max Activating Token Index: 301