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

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

Neuron 3011 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: 0.6807. Min Range: -0.6807

Max Act: 0.6807. Min Act: -0.0000

Data Index: 108095 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1619640 (Python Code)

Max Activating Token Index: 354

Text #2

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4943. Min Act: 0.0000

Data Index: 1515124 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1547805 (Python Code)

Max Activating Token Index: 429

Text #4

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5023. Min Act: -0.0000

Data Index: 963079 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1410264 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1598562 (Python Code)

Max Activating Token Index: 717

Text #7

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1377371 (Python Code)

Max Activating Token Index: 848

Text #8

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1655571 (Python Code)

Max Activating Token Index: 136

Text #9

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1434505 (Python Code)

Max Activating Token Index: 641

Text #10

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4420. Min Act: 0.0000

Data Index: 1605793 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1645176 (Python Code)

Max Activating Token Index: 688

Text #12

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1530045 (Python Code)

Max Activating Token Index: 919

Text #13

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1603456 (Python Code)

Max Activating Token Index: 246

Text #14

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1498888 (Python Code)

Max Activating Token Index: 213

Text #15

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1383055 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1415639 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1601111 (Python Code)

Max Activating Token Index: 808

Text #18

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1374427 (Python Code)

Max Activating Token Index: 689

Text #19

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1380129 (Python Code)

Max Activating Token Index: 1003