Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1953 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1730. Min Act: -0.0001

Data Index: 480196 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1678. Min Act: -0.0001

Data Index: 372548 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1787. Min Act: -0.0001

Data Index: 582133 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1259232 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1586. Min Act: -0.0001

Data Index: 951429 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1567. Min Act: -0.0001

Data Index: 518858 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1594. Min Act: -0.0001

Data Index: 852013 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1004889 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1631. Min Act: -0.0001

Data Index: 906083 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1581. Min Act: -0.0001

Data Index: 1289001 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1543. Min Act: -0.0001

Data Index: 711776 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1499. Min Act: -0.0001

Data Index: 385036 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1545. Min Act: -0.0001

Data Index: 1092356 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1433. Min Act: -0.0001

Data Index: 803828 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1529. Min Act: -0.0001

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1364. Min Act: -0.0001

Data Index: 159969 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1545. Min Act: -0.0001

Data Index: 648585 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1367. Min Act: -0.0001

Data Index: 351807 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1449. Min Act: -0.0001

Data Index: 948712 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1294640 (C4 (Web Text))

Max Activating Token Index: 328