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

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

Neuron 1911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1014. Min Range: -3.1014

Max Act: 3.1014. Min Act: -0.0000

Data Index: 1364531 (Python Code)

Max Activating Token Index: 856

Text #1

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.9346. Min Act: -0.0000

Data Index: 1501343 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 3.1014. Min Range: -3.1014

Max Act: 3.0276. Min Act: -0.0000

Data Index: 1437292 (Python Code)

Max Activating Token Index: 644

Text #3

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.9548. Min Act: -0.0000

Data Index: 1520943 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.5415. Min Act: -0.0000

Data Index: 1501599 (Python Code)

Max Activating Token Index: 163

Text #5

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.3027. Min Act: -0.0000

Data Index: 1649473 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.2900. Min Act: -0.0000

Data Index: 1415305 (Python Code)

Max Activating Token Index: 340

Text #7

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.1395. Min Act: -0.0000

Data Index: 1446104 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.3732. Min Act: -0.0000

Data Index: 1397806 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.3820. Min Act: -0.0000

Data Index: 1436831 (Python Code)

Max Activating Token Index: 385

Text #10

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.3467. Min Act: -0.0000

Data Index: 1631152 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.2912. Min Act: -0.0000

Data Index: 1613836 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.2904. Min Act: -0.0000

Data Index: 1459744 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.2706. Min Act: -0.0000

Data Index: 1459456 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.2047. Min Act: -0.0001

Data Index: 1590314 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.0750. Min Act: -0.0000

Data Index: 1433938 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.1864. Min Act: -0.0000

Data Index: 1620216 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.1588. Min Act: -0.0000

Data Index: 1393294 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.1117. Min Act: -0.0000

Data Index: 1645173 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.1169. Min Act: -0.0000

Data Index: 1459830 (Python Code)

Max Activating Token Index: 870