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

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

Neuron 4096 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.1581. Min Act: -0.0000

Data Index: 724635 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0517. Min Act: -0.0000

Data Index: 453152 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0452. Min Act: -0.0000

Data Index: 798168 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 1.1581. Min Range: -1.1581

Max Act: 1.0268. Min Act: -0.0000

Data Index: 787430 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1007366 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.9302. Min Act: -0.0000

Data Index: 107671 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8778. Min Act: -0.0001

Data Index: 366425 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8335. Min Act: -0.0000

Data Index: 680196 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8781. Min Act: -0.0001

Data Index: 886147 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.7719. Min Act: -0.0000

Data Index: 368247 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1008994 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8496. Min Act: -0.0000

Data Index: 123136 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8203. Min Act: -0.0000

Data Index: 299570 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1129691 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8020. Min Act: -0.0000

Data Index: 981843 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.7702. Min Act: -0.0000

Data Index: 216788 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.7750. Min Act: -0.0000

Data Index: 49674 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.7671. Min Act: -0.0001

Data Index: 51629 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.7662. Min Act: -0.0001

Data Index: 598673 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 1.1581. Min Range: -1.1581

Max Act: 0.8102. Min Act: -0.0000

Data Index: 538738 (C4 (Web Text))

Max Activating Token Index: 77