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

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

Neuron 3964 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: 1.4597. Min Range: -1.4597

Max Act: 1.4597. Min Act: -0.0000

Data Index: 1405403 (Python Code)

Max Activating Token Index: 108

Text #1

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.2525. Min Act: -0.0000

Data Index: 865126 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.1551. Min Act: -0.0000

Data Index: 163760 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9863. Min Act: -0.0000

Data Index: 475369 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1386511 (Python Code)

Max Activating Token Index: 399

Text #5

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1239603 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.1498. Min Act: -0.0000

Data Index: 346742 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9799. Min Act: -0.0000

Data Index: 827758 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9958. Min Act: -0.0000

Data Index: 1625757 (Python Code)

Max Activating Token Index: 336

Text #9

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9507. Min Act: -0.0000

Data Index: 246752 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.8327. Min Act: -0.0000

Data Index: 711725 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.8602. Min Act: -0.0000

Data Index: 191257 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.8807. Min Act: -0.0000

Data Index: 297156 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.8704. Min Act: -0.0000

Data Index: 373892 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 1.4597. Min Range: -1.4597

Max Act: 1.0240. Min Act: -0.0000

Data Index: 591289 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9269. Min Act: -0.0000

Data Index: 916257 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9465. Min Act: -0.0000

Data Index: 878276 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1080683 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.9139. Min Act: -0.0000

Data Index: 200895 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.4597. Min Range: -1.4597

Max Act: 0.8354. Min Act: -0.0000

Data Index: 949572 (C4 (Web Text))

Max Activating Token Index: 294