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

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

Neuron 1653 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.3194. Min Act: -0.0001

Data Index: 627755 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.5686. Min Act: -0.0001

Data Index: 79643 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.5772. Min Act: -0.0001

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.2278. Min Act: -0.0001

Data Index: 209096 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.2032. Min Act: -0.0001

Data Index: 612942 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.3439. Min Act: -0.0001

Data Index: 927805 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.2004. Min Act: -0.0001

Data Index: 255684 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.0288. Min Act: -0.0001

Data Index: 115748 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.5772. Min Range: -3.5772

Max Act: 2.9977. Min Act: -0.0001

Data Index: 1168214 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 3.5772. Min Range: -3.5772

Max Act: 2.9559. Min Act: -0.0001

Data Index: 109623 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 3.5772. Min Range: -3.5772

Max Act: 2.9303. Min Act: -0.0001

Data Index: 326852 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.2099. Min Act: -0.0001

Data Index: 6941 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.1627. Min Act: -0.0001

Data Index: 330873 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.0164. Min Act: -0.0001

Data Index: 671929 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.0096. Min Act: -0.0001

Data Index: 558038 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 3.5772. Min Range: -3.5772

Max Act: 2.8255. Min Act: -0.0001

Data Index: 1060937 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.5772. Min Range: -3.5772

Max Act: 2.7518. Min Act: -0.0001

Data Index: 130606 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 3.5772. Min Range: -3.5772

Max Act: 3.1490. Min Act: -0.0001

Data Index: 809737 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 3.5772. Min Range: -3.5772

Max Act: 2.9360. Min Act: -0.0001

Data Index: 1213725 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 3.5772. Min Range: -3.5772

Max Act: 2.8053. Min Act: -0.0001

Data Index: 1271085 (C4 (Web Text))

Max Activating Token Index: 679