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

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

Neuron 3728 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3796. Min Range: -2.3796

Max Act: 2.3796. Min Act: -0.0000

Data Index: 151941 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 2.3796. Min Range: -2.3796

Max Act: 2.1196. Min Act: -0.0000

Data Index: 1274503 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.8753. Min Act: -0.0000

Data Index: 778645 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.3888. Min Act: -0.0000

Data Index: 982027 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.3788. Min Act: -0.0000

Data Index: 80238 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.3688. Min Act: -0.0000

Data Index: 544860 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1176731 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.3406. Min Act: -0.0000

Data Index: 233143 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1219338 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.3529. Min Act: -0.0000

Data Index: 612500 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1182250 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.2772. Min Act: -0.0000

Data Index: 820106 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.2557. Min Act: -0.0000

Data Index: 44740 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.1588. Min Act: -0.0000

Data Index: 475664 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1202835 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.1274. Min Act: -0.0000

Data Index: 757507 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1352261 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1107691 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.1907. Min Act: -0.0000

Data Index: 496171 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.1807. Min Act: -0.0000

Data Index: 497947 (C4 (Web Text))

Max Activating Token Index: 282