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

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

Neuron 1213 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: 1.1597. Min Range: -1.1597

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1034356 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.1597. Min Range: -1.1597

Max Act: 1.0860. Min Act: -0.0000

Data Index: 1187685 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 1.1597. Min Range: -1.1597

Max Act: 1.0018. Min Act: -0.0000

Data Index: 955623 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1035435 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.1597. Min Range: -1.1597

Max Act: 1.0703. Min Act: -0.0000

Data Index: 7862 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9483. Min Act: -0.0000

Data Index: 359591 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9672. Min Act: -0.0000

Data Index: 263946 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.1597. Min Range: -1.1597

Max Act: 1.0508. Min Act: -0.0000

Data Index: 225699 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8682. Min Act: -0.0000

Data Index: 565173 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1031631 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.9613. Min Act: -0.0000

Data Index: 616917 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8650. Min Act: -0.0000

Data Index: 303537 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8668. Min Act: -0.0000

Data Index: 362963 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8214. Min Act: -0.0000

Data Index: 666223 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8057. Min Act: -0.0000

Data Index: 862156 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7858. Min Act: -0.0000

Data Index: 896226 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7759. Min Act: -0.0000

Data Index: 910545 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.8218. Min Act: -0.0000

Data Index: 312614 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1034012 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.1597. Min Range: -1.1597

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1187888 (C4 (Web Text))

Max Activating Token Index: 878