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

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

Neuron 4769 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0577. Min Range: -1.0577

Max Act: 1.0103. Min Act: -0.0001

Data Index: 397647 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 1.0577. Min Range: -1.0577

Max Act: 1.0388. Min Act: -0.0001

Data Index: 237423 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 1.0577. Min Range: -1.0577

Max Act: 1.0577. Min Act: -0.0001

Data Index: 455771 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.9767. Min Act: -0.0001

Data Index: 1199138 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.0577. Min Range: -1.0577

Max Act: 1.0447. Min Act: -0.0001

Data Index: 51040 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.9327. Min Act: -0.0001

Data Index: 563846 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.9589. Min Act: -0.0001

Data Index: 1082617 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.9129. Min Act: -0.0001

Data Index: 181398 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.9030. Min Act: -0.0001

Data Index: 790682 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8087. Min Act: -0.0001

Data Index: 455783 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.9124. Min Act: -0.0001

Data Index: 528197 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7760. Min Act: -0.0001

Data Index: 850799 (C4 (Web Text))

Max Activating Token Index: 707

Text #12

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8731. Min Act: -0.0001

Data Index: 682862 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8739. Min Act: -0.0001

Data Index: 394750 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8406. Min Act: -0.0001

Data Index: 292838 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.8650. Min Act: -0.0001

Data Index: 46945 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7888. Min Act: -0.0001

Data Index: 389457 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7331. Min Act: -0.0001

Data Index: 279487 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7887. Min Act: -0.0001

Data Index: 192630 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 1.0577. Min Range: -1.0577

Max Act: 0.7921. Min Act: -0.0001

Data Index: 760834 (C4 (Web Text))

Max Activating Token Index: 478