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

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

Neuron 5063 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: 0.2321. Min Range: -0.2321

Max Act: 0.2297. Min Act: -0.0000

Data Index: 920078 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2321. Min Act: -0.0000

Data Index: 641730 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2095. Min Act: -0.0000

Data Index: 326269 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2123. Min Act: -0.0000

Data Index: 993707 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1314426 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1184792 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1870. Min Act: 0.0000

Data Index: 1052067 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1708. Min Act: 0.0000

Data Index: 81442 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1520685 (Python Code)

Max Activating Token Index: 492

Text #9

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1481. Min Act: -0.0000

Data Index: 731594 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1493. Min Act: 0.0000

Data Index: 1333814 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1439. Min Act: 0.0000

Data Index: 839692 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1351. Min Act: 0.0000

Data Index: 869829 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1458. Min Act: 0.0000

Data Index: 1069569 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1455. Min Act: 0.0000

Data Index: 447764 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1435. Min Act: -0.0000

Data Index: 743060 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1416. Min Act: -0.0000

Data Index: 314884 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1373. Min Act: -0.0000

Data Index: 804607 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1244. Min Act: -0.0000

Data Index: 217419 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1414477 (Python Code)

Max Activating Token Index: 91