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

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

Neuron 2284 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: 0.4418. Min Range: -0.4418

Max Act: 0.4418. Min Act: -0.0001

Data Index: 575577 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.4072. Min Act: -0.0001

Data Index: 1040771 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3774. Min Act: -0.0001

Data Index: 265454 (C4 (Web Text))

Max Activating Token Index: 624

Text #3

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3757. Min Act: -0.0001

Data Index: 300008 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3805. Min Act: -0.0001

Data Index: 485872 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3496. Min Act: -0.0001

Data Index: 567077 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3734. Min Act: -0.0001

Data Index: 1222683 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3560. Min Act: -0.0001

Data Index: 998184 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3531. Min Act: -0.0001

Data Index: 537866 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3658. Min Act: -0.0001

Data Index: 825796 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3506. Min Act: -0.0001

Data Index: 1019837 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3443. Min Act: -0.0001

Data Index: 1296943 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3442. Min Act: -0.0001

Data Index: 195758 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3447. Min Act: -0.0001

Data Index: 441323 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1173443 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1231674 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3251. Min Act: -0.0001

Data Index: 230787 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3245. Min Act: -0.0001

Data Index: 698313 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3333. Min Act: -0.0001

Data Index: 934534 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.4418. Min Range: -0.4418

Max Act: 0.3292. Min Act: -0.0001

Data Index: 876493 (C4 (Web Text))

Max Activating Token Index: 777