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

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

Neuron 6094 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.2006. Min Act: -0.0000

Data Index: 178857 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1342870 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.0418. Min Act: -0.0000

Data Index: 686957 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1037887 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9999. Min Act: -0.0000

Data Index: 833387 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.0387. Min Act: -0.0000

Data Index: 202099 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9437. Min Act: -0.0000

Data Index: 705477 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9880. Min Act: -0.0000

Data Index: 295535 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 1.2006. Min Range: -1.2006

Max Act: 1.0231. Min Act: -0.0000

Data Index: 445143 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9819. Min Act: -0.0000

Data Index: 105255 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9481. Min Act: -0.0000

Data Index: 831512 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9747. Min Act: -0.0000

Data Index: 589659 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1021152 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9943. Min Act: -0.0000

Data Index: 549917 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9859. Min Act: -0.0000

Data Index: 258203 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1237550 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1158896 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1174194 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.9399. Min Act: -0.0000

Data Index: 799834 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.2006. Min Range: -1.2006

Max Act: 0.8501. Min Act: -0.0000

Data Index: 376927 (C4 (Web Text))

Max Activating Token Index: 212