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

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

Neuron 1932 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: 0.7608. Min Range: -0.7608

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1478927 (Python Code)

Max Activating Token Index: 285

Text #1

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.6071. Min Act: -0.0000

Data Index: 1497429 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1610605 (Python Code)

Max Activating Token Index: 394

Text #3

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1575642 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5253. Min Act: 0.0000

Data Index: 1383001 (Python Code)

Max Activating Token Index: 61

Text #5

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4997. Min Act: -0.0000

Data Index: 93965 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1623133 (Python Code)

Max Activating Token Index: 197

Text #7

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1120714 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1607355 (Python Code)

Max Activating Token Index: 849

Text #9

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4770. Min Act: -0.0000

Data Index: 537188 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1241688 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1478730 (Python Code)

Max Activating Token Index: 274

Text #12

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1383187 (Python Code)

Max Activating Token Index: 640

Text #13

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4293. Min Act: -0.0000

Data Index: 530137 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4297. Min Act: -0.0000

Data Index: 308939 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4623. Min Act: -0.0000

Data Index: 1550598 (Python Code)

Max Activating Token Index: 592

Text #16

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1439877 (Python Code)

Max Activating Token Index: 370

Text #17

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4084. Min Act: -0.0000

Data Index: 1638977 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1609920 (Python Code)

Max Activating Token Index: 280

Text #19

Max Range: 0.7608. Min Range: -0.7608

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1625391 (Python Code)

Max Activating Token Index: 689