Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2590 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0000

Data Index: 93632 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0657. Min Act: -0.0000

Data Index: 740906 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0649. Min Act: -0.0000

Data Index: 281918 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1130739 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0648. Min Act: -0.0000

Data Index: 490414 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0643. Min Act: -0.0000

Data Index: 428791 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0570. Min Act: -0.0000

Data Index: 744129 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1015574 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0563. Min Act: 0.0000

Data Index: 981640 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0559. Min Act: -0.0000

Data Index: 79485 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0559. Min Act: -0.0000

Data Index: 251211 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0568. Min Act: -0.0000

Data Index: 726270 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0546. Min Act: 0.0000

Data Index: 602129 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0501. Min Act: 0.0000

Data Index: 193830 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0514. Min Act: -0.0000

Data Index: 840023 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0523. Min Act: 0.0000

Data Index: 153273 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1567338 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1327183 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0513. Min Act: -0.0000

Data Index: 1302264 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1032362 (C4 (Web Text))

Max Activating Token Index: 849