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

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

Neuron 1706 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.8006. Min Act: -0.0001

Data Index: 348631 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.8435. Min Act: -0.0001

Data Index: 623127 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.8351. Min Act: -0.0001

Data Index: 1034688 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.9020. Min Act: -0.0001

Data Index: 775224 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7413. Min Act: -0.0001

Data Index: 1049885 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7780. Min Act: -0.0001

Data Index: 1287716 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7684. Min Act: -0.0001

Data Index: 945419 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7479. Min Act: -0.0001

Data Index: 647584 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7538. Min Act: -0.0001

Data Index: 107629 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7593. Min Act: -0.0001

Data Index: 730805 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7236. Min Act: -0.0001

Data Index: 939860 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6962. Min Act: -0.0001

Data Index: 1320816 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7679. Min Act: -0.0001

Data Index: 786098 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.5816. Min Act: -0.0001

Data Index: 918341 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7296. Min Act: -0.0001

Data Index: 879622 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6760. Min Act: -0.0001

Data Index: 616887 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6773. Min Act: -0.0001

Data Index: 655715 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7330. Min Act: -0.0001

Data Index: 110823 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6062. Min Act: -0.0001

Data Index: 610472 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6702. Min Act: -0.0001

Data Index: 275995 (C4 (Web Text))

Max Activating Token Index: 864