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

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

Neuron 411 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.9479. Min Act: -0.0002

Data Index: 1438144 (Python Code)

Max Activating Token Index: 351

Text #1

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.8238. Min Act: -0.0002

Data Index: 1462306 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.8909. Min Act: -0.0002

Data Index: 1458439 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7943. Min Act: -0.0002

Data Index: 1610274 (Python Code)

Max Activating Token Index: 790

Text #4

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7437. Min Act: -0.0002

Data Index: 1474967 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.8442. Min Act: -0.0002

Data Index: 1646396 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7112. Min Act: -0.0002

Data Index: 1557428 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7078. Min Act: -0.0002

Data Index: 1596139 (Python Code)

Max Activating Token Index: 323

Text #8

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6936. Min Act: -0.0002

Data Index: 1485118 (Python Code)

Max Activating Token Index: 322

Text #9

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7154. Min Act: -0.0002

Data Index: 1590450 (Python Code)

Max Activating Token Index: 240

Text #10

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7105. Min Act: -0.0002

Data Index: 1501936 (Python Code)

Max Activating Token Index: 839

Text #11

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6805. Min Act: -0.0002

Data Index: 1482548 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6846. Min Act: -0.0002

Data Index: 1444140 (Python Code)

Max Activating Token Index: 301

Text #13

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7239. Min Act: -0.0002

Data Index: 1620282 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6199. Min Act: -0.0002

Data Index: 1487734 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6927. Min Act: -0.0002

Data Index: 1560779 (Python Code)

Max Activating Token Index: 334

Text #16

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7154. Min Act: -0.0002

Data Index: 1477462 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6820. Min Act: -0.0002

Data Index: 1645294 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.6520. Min Act: -0.0002

Data Index: 1556098 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 0.9479. Min Range: -0.9479

Max Act: 0.7391. Min Act: -0.0002

Data Index: 1494932 (Python Code)

Max Activating Token Index: 890