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

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

Neuron 4172 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1491414 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1452776 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1648274 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1446342 (Python Code)

Max Activating Token Index: 893

Text #4

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1612280 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7300. Min Act: -0.0000

Data Index: 851215 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6806. Min Act: -0.0000

Data Index: 827826 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6316. Min Act: -0.0000

Data Index: 460364 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6340. Min Act: -0.0000

Data Index: 148722 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1643287 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1337593 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6293. Min Act: -0.0000

Data Index: 810320 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1592306 (Python Code)

Max Activating Token Index: 343

Text #13

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6082. Min Act: -0.0000

Data Index: 357248 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5549. Min Act: -0.0000

Data Index: 168598 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1553749 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5600. Min Act: -0.0000

Data Index: 130085 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5306. Min Act: -0.0000

Data Index: 932504 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1510224 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.5541. Min Act: -0.0000

Data Index: 283561 (C4 (Web Text))

Max Activating Token Index: 357