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

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

Neuron 3203 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: 1.1662. Min Range: -1.1662

Max Act: 1.1594. Min Act: -0.0000

Data Index: 792241 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.1331. Min Act: -0.0000

Data Index: 556086 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.1662. Min Act: -0.0000

Data Index: 879532 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9998. Min Act: -0.0000

Data Index: 818527 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0581. Min Act: -0.0000

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0414. Min Act: -0.0000

Data Index: 1344649 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0038. Min Act: -0.0000

Data Index: 476117 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0018. Min Act: -0.0000

Data Index: 410054 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0395. Min Act: -0.0000

Data Index: 22607 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8902. Min Act: -0.0000

Data Index: 457055 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1055934 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1219179 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.1662. Min Range: -1.1662

Max Act: 1.0002. Min Act: -0.0000

Data Index: 622749 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9473. Min Act: -0.0000

Data Index: 855392 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9105. Min Act: -0.0000

Data Index: 333398 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9256. Min Act: -0.0000

Data Index: 1009151 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9464. Min Act: -0.0000

Data Index: 162195 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9837. Min Act: -0.0000

Data Index: 793746 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1073365 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.1662. Min Range: -1.1662

Max Act: 0.9063. Min Act: -0.0000

Data Index: 869220 (C4 (Web Text))

Max Activating Token Index: 942