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

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

Neuron 4201 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6780. Min Act: 0.0000

Data Index: 1630713 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.7016. Min Act: 0.0000

Data Index: 1479058 (Python Code)

Max Activating Token Index: 139

Text #2

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1605063 (Python Code)

Max Activating Token Index: 470

Text #3

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6410. Min Act: 0.0000

Data Index: 1555159 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.6075. Min Act: 0.0000

Data Index: 1389993 (Python Code)

Max Activating Token Index: 828

Text #5

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1515137 (Python Code)

Max Activating Token Index: 858

Text #6

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5532. Min Act: 0.0000

Data Index: 1640291 (Python Code)

Max Activating Token Index: 426

Text #7

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5437. Min Act: 0.0000

Data Index: 1392847 (Python Code)

Max Activating Token Index: 418

Text #8

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5503. Min Act: 0.0000

Data Index: 1641713 (Python Code)

Max Activating Token Index: 854

Text #9

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1655066 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1413343 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1515478 (Python Code)

Max Activating Token Index: 823

Text #12

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1497671 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1433502 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1632995 (Python Code)

Max Activating Token Index: 866

Text #15

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4990. Min Act: -0.0000

Data Index: 154297 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1630806 (Python Code)

Max Activating Token Index: 640

Text #17

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4695. Min Act: 0.0000

Data Index: 1382991 (Python Code)

Max Activating Token Index: 323

Text #18

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1527669 (Python Code)

Max Activating Token Index: 203

Text #19

Max Range: 0.7016. Min Range: -0.7016

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1425133 (Python Code)

Max Activating Token Index: 366