Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1743 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2699. Min Act: -0.0001

Data Index: 385557 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2209. Min Act: -0.0000

Data Index: 786393 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2038. Min Act: -0.0000

Data Index: 582435 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1095458 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1894. Min Act: -0.0001

Data Index: 102702 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1313632 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1759. Min Act: -0.0000

Data Index: 989974 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1803. Min Act: -0.0001

Data Index: 217744 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1177671 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1155889 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1025344 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1055377 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1472. Min Act: -0.0000

Data Index: 575424 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1006207 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1519. Min Act: -0.0001

Data Index: 49926 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1062918 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1568. Min Act: -0.0000

Data Index: 275455 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1442. Min Act: -0.0000

Data Index: 500536 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1483. Min Act: -0.0000

Data Index: 464852 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1524. Min Act: -0.0001

Data Index: 924337 (C4 (Web Text))

Max Activating Token Index: 25