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

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

Neuron 3174 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.8135. Min Act: -0.0001

Data Index: 857513 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6759. Min Act: -0.0000

Data Index: 839837 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6638. Min Act: -0.0000

Data Index: 961260 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6359. Min Act: -0.0001

Data Index: 400690 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6013. Min Act: -0.0001

Data Index: 485647 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6211. Min Act: -0.0001

Data Index: 791639 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6159. Min Act: -0.0001

Data Index: 795099 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5788. Min Act: -0.0001

Data Index: 933738 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.6115. Min Act: -0.0000

Data Index: 453616 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5702. Min Act: -0.0000

Data Index: 672326 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5806. Min Act: -0.0001

Data Index: 736331 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5688. Min Act: -0.0001

Data Index: 1338148 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5332. Min Act: -0.0000

Data Index: 100956 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5493. Min Act: -0.0001

Data Index: 129378 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5258. Min Act: -0.0001

Data Index: 1095516 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5486. Min Act: -0.0001

Data Index: 1245453 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1071838 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5853. Min Act: -0.0001

Data Index: 734097 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5402. Min Act: -0.0001

Data Index: 422249 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.8135. Min Range: -0.8135

Max Act: 0.5242. Min Act: -0.0001

Data Index: 1284884 (C4 (Web Text))

Max Activating Token Index: 916