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

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

Neuron 2347 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.6036. Min Act: -0.0000

Data Index: 1442831 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1499131 (Python Code)

Max Activating Token Index: 216

Text #2

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1445799 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0685. Min Act: -0.0001

Data Index: 1594931 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.1243. Min Act: -0.0001

Data Index: 1638455 (Python Code)

Max Activating Token Index: 146

Text #5

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1633458 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.1240. Min Act: -0.0001

Data Index: 1652412 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1409646 (Python Code)

Max Activating Token Index: 456

Text #8

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.1778. Min Act: -0.0001

Data Index: 1454005 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.1254. Min Act: -0.0001

Data Index: 1493029 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.1963. Min Act: -0.0001

Data Index: 1544344 (Python Code)

Max Activating Token Index: 95

Text #11

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0732. Min Act: -0.0001

Data Index: 1627430 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0835. Min Act: -0.0001

Data Index: 1609834 (Python Code)

Max Activating Token Index: 205

Text #13

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1649312 (Python Code)

Max Activating Token Index: 23

Text #14

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1566305 (Python Code)

Max Activating Token Index: 521

Text #15

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0348. Min Act: -0.0001

Data Index: 1445518 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0807. Min Act: -0.0000

Data Index: 1514435 (Python Code)

Max Activating Token Index: 260

Text #17

Max Range: 1.6036. Min Range: -1.6036

Max Act: 0.9335. Min Act: -0.0001

Data Index: 1546601 (Python Code)

Max Activating Token Index: 576

Text #18

Max Range: 1.6036. Min Range: -1.6036

Max Act: 0.9852. Min Act: -0.0001

Data Index: 1496793 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 1.6036. Min Range: -1.6036

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1606010 (Python Code)

Max Activating Token Index: 351