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

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

Neuron 1737 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1066224 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1060977 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 1.2108. Min Range: -1.2108

Max Act: 1.0013. Min Act: -0.0000

Data Index: 238352 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9998. Min Act: -0.0000

Data Index: 1126660 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9220. Min Act: -0.0000

Data Index: 885966 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9826. Min Act: -0.0000

Data Index: 3883 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9479. Min Act: -0.0000

Data Index: 186699 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1033294 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8796. Min Act: -0.0000

Data Index: 972619 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.9251. Min Act: -0.0000

Data Index: 87062 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8563. Min Act: -0.0000

Data Index: 897172 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8914. Min Act: -0.0000

Data Index: 10131 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1108596 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8671. Min Act: -0.0000

Data Index: 272222 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8662. Min Act: -0.0000

Data Index: 936626 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8538. Min Act: -0.0000

Data Index: 770307 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8553. Min Act: -0.0000

Data Index: 656274 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1049324 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8464. Min Act: -0.0000

Data Index: 2544 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.2108. Min Range: -1.2108

Max Act: 0.8416. Min Act: -0.0000

Data Index: 753387 (C4 (Web Text))

Max Activating Token Index: 723