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

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

Neuron 694 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0719. Min Act: -0.0000

Data Index: 658578 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1076267 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0562. Min Act: -0.0000

Data Index: 432030 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0553. Min Act: -0.0000

Data Index: 217683 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1343952 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0438. Min Act: -0.0000

Data Index: 159202 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1242553 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1046755 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1370516 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0396. Min Act: -0.0000

Data Index: 772644 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1135556 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1089667 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0496. Min Act: -0.0000

Data Index: 385370 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0471. Min Act: -0.0000

Data Index: 1111609 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0485. Min Act: -0.0000

Data Index: 656643 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0487. Min Act: -0.0000

Data Index: 990438 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0440. Min Act: -0.0000

Data Index: 1395644 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1137043 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0594. Min Act: -0.0000

Data Index: 1580080 (Python Code)

Max Activating Token Index: 859

Text #19

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0446. Min Act: -0.0000

Data Index: 994784 (C4 (Web Text))

Max Activating Token Index: 127