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

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

Neuron 4320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1721. Min Act: -0.0001

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1733. Min Act: -0.0001

Data Index: 945181 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1661. Min Act: -0.0001

Data Index: 544039 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0001

Data Index: 408541 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1136467 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1699. Min Act: -0.0001

Data Index: 554656 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1738. Min Act: -0.0001

Data Index: 1077818 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1628. Min Act: -0.0001

Data Index: 496199 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1533. Min Act: -0.0001

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1311732 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1564. Min Act: -0.0001

Data Index: 478271 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1551. Min Act: -0.0001

Data Index: 483403 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1004801 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1486. Min Act: -0.0001

Data Index: 671769 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1516. Min Act: -0.0001

Data Index: 775794 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1382. Min Act: -0.0001

Data Index: 222925 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1322. Min Act: -0.0001

Data Index: 379927 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1408. Min Act: -0.0001

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1458. Min Act: -0.0001

Data Index: 417993 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1508. Min Act: -0.0001

Data Index: 260050 (C4 (Web Text))

Max Activating Token Index: 351