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

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

Neuron 2301 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: 0.2324. Min Range: -0.2324

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1438202 (Python Code)

Max Activating Token Index: 220

Text #1

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1386025 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2224. Min Act: 0.0000

Data Index: 1467401 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1537381 (Python Code)

Max Activating Token Index: 593

Text #4

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1591450 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1394351 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.2039. Min Act: 0.0000

Data Index: 1599105 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1545225 (Python Code)

Max Activating Token Index: 206

Text #8

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1848. Min Act: -0.0000

Data Index: 927138 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1897. Min Act: 0.0000

Data Index: 1390925 (Python Code)

Max Activating Token Index: 461

Text #10

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1379932 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1614700 (Python Code)

Max Activating Token Index: 905

Text #12

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1610729 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1389946 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1372442 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1433794 (Python Code)

Max Activating Token Index: 139

Text #16

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1441933 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1405389 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1593905 (Python Code)

Max Activating Token Index: 260

Text #19

Max Range: 0.2324. Min Range: -0.2324

Max Act: 0.1710. Min Act: 0.0000

Data Index: 1646387 (Python Code)

Max Activating Token Index: 261