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

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

Neuron 2588 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: 1.7894. Min Range: -1.7894

Max Act: 1.7894. Min Act: -0.0000

Data Index: 340957 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.4391. Min Act: -0.0000

Data Index: 1630972 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.3418. Min Act: -0.0000

Data Index: 11877 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.4086. Min Act: -0.0000

Data Index: 73602 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1416223 (Python Code)

Max Activating Token Index: 337

Text #5

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.3662. Min Act: -0.0000

Data Index: 1559633 (Python Code)

Max Activating Token Index: 110

Text #6

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1468407 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.2735. Min Act: -0.0000

Data Index: 1649478 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.3191. Min Act: -0.0000

Data Index: 1566604 (Python Code)

Max Activating Token Index: 972

Text #9

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1713. Min Act: -0.0000

Data Index: 1556382 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1367969 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1538108 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1443329 (Python Code)

Max Activating Token Index: 196

Text #13

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1402525 (Python Code)

Max Activating Token Index: 740

Text #14

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.2955. Min Act: -0.0000

Data Index: 1446453 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1258. Min Act: -0.0000

Data Index: 1475572 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1303. Min Act: -0.0000

Data Index: 855373 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1178. Min Act: -0.0000

Data Index: 482407 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1595. Min Act: -0.0000

Data Index: 1593641 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 1.7894. Min Range: -1.7894

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1566693 (Python Code)

Max Activating Token Index: 771