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

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

Neuron 2526 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.4038. Min Act: -0.0000

Data Index: 251431 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3654. Min Act: -0.0000

Data Index: 600099 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3668. Min Act: -0.0001

Data Index: 375563 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3575. Min Act: -0.0000

Data Index: 32178 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3706. Min Act: -0.0000

Data Index: 91954 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1045211 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1317984 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.3152. Min Act: -0.0001

Data Index: 193309 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2890. Min Act: -0.0000

Data Index: 540705 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2864. Min Act: -0.0000

Data Index: 472384 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2792. Min Act: -0.0000

Data Index: 42536 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2926. Min Act: -0.0000

Data Index: 609469 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1064822 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2852. Min Act: -0.0001

Data Index: 416800 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2829. Min Act: -0.0001

Data Index: 118019 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1111081 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1273303 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2776. Min Act: -0.0001

Data Index: 1466365 (Python Code)

Max Activating Token Index: 444

Text #18

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2545. Min Act: -0.0000

Data Index: 304311 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 0.4038. Min Range: -0.4038

Max Act: 0.2618. Min Act: -0.0000

Data Index: 792244 (C4 (Web Text))

Max Activating Token Index: 28