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

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

Neuron 1655 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: 0.2572. Min Range: -0.2572

Max Act: 0.2572. Min Act: -0.0001

Data Index: 465320 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1288429 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1887. Min Act: -0.0001

Data Index: 418370 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1807. Min Act: -0.0001

Data Index: 59426 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1607. Min Act: -0.0001

Data Index: 679340 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1810. Min Act: -0.0001

Data Index: 420238 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1676. Min Act: -0.0001

Data Index: 173862 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1021417 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1609. Min Act: -0.0001

Data Index: 539363 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1093311 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1056041 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1513. Min Act: -0.0001

Data Index: 477194 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1656. Min Act: -0.0001

Data Index: 924533 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1456. Min Act: -0.0001

Data Index: 654306 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1398. Min Act: -0.0001

Data Index: 968566 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1242539 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1310481 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1415. Min Act: -0.0001

Data Index: 577760 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1001980 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1454. Min Act: -0.0001

Data Index: 294815 (C4 (Web Text))

Max Activating Token Index: 779