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

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

Neuron 3378 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2637. Min Act: -0.0000

Data Index: 154550 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2540. Min Act: -0.0000

Data Index: 626403 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2572. Min Act: -0.0000

Data Index: 680547 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2391. Min Act: -0.0000

Data Index: 891677 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2349. Min Act: -0.0000

Data Index: 824630 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1138791 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2266. Min Act: -0.0000

Data Index: 837008 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1060559 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2197. Min Act: -0.0000

Data Index: 258825 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2136. Min Act: -0.0000

Data Index: 66124 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.2214. Min Act: -0.0000

Data Index: 21442 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1604388 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1854. Min Act: -0.0000

Data Index: 589938 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1789. Min Act: 0.0000

Data Index: 1556098 (Python Code)

Max Activating Token Index: 294

Text #14

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1279475 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1775. Min Act: -0.0000

Data Index: 380352 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1429083 (Python Code)

Max Activating Token Index: 690

Text #17

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1600067 (Python Code)

Max Activating Token Index: 617

Text #18

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1627. Min Act: -0.0000

Data Index: 1540186 (Python Code)

Max Activating Token Index: 762

Text #19

Max Range: 0.2637. Min Range: -0.2637

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1024447 (C4 (Web Text))

Max Activating Token Index: 227