Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3415 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2180. Min Range: -2.2180

Max Act: 2.2180. Min Act: -0.0000

Data Index: 1363786 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.7791. Min Act: -0.0000

Data Index: 1425298 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1498813 (Python Code)

Max Activating Token Index: 889

Text #3

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.5833. Min Act: -0.0000

Data Index: 1496403 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.3820. Min Act: -0.0000

Data Index: 1577024 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.4304. Min Act: -0.0000

Data Index: 1532466 (Python Code)

Max Activating Token Index: 602

Text #6

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1619527 (Python Code)

Max Activating Token Index: 953

Text #7

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1419172 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1600354 (Python Code)

Max Activating Token Index: 302

Text #9

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.3186. Min Act: -0.0000

Data Index: 1515026 (Python Code)

Max Activating Token Index: 617

Text #10

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1598810 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.2994. Min Act: -0.0000

Data Index: 1528658 (Python Code)

Max Activating Token Index: 590

Text #12

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.2843. Min Act: -0.0000

Data Index: 1612808 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1502474 (Python Code)

Max Activating Token Index: 843

Text #14

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1377834 (Python Code)

Max Activating Token Index: 878

Text #15

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1635815 (Python Code)

Max Activating Token Index: 419

Text #16

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1504846 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1437230 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1557678 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 2.2180. Min Range: -2.2180

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1472577 (Python Code)

Max Activating Token Index: 778