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

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

Neuron 3516 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.7107. Min Act: -0.0001

Data Index: 1241582 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1148396 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1214370 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5601. Min Act: -0.0000

Data Index: 829922 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5128. Min Act: -0.0001

Data Index: 1137620 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5070. Min Act: -0.0001

Data Index: 40368 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5133. Min Act: -0.0001

Data Index: 991781 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5001. Min Act: -0.0000

Data Index: 125859 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5531. Min Act: -0.0000

Data Index: 874603 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5129. Min Act: -0.0000

Data Index: 675606 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4741. Min Act: -0.0001

Data Index: 1004162 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4732. Min Act: -0.0000

Data Index: 310599 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5063. Min Act: -0.0000

Data Index: 702756 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4884. Min Act: -0.0001

Data Index: 18547 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4597. Min Act: -0.0001

Data Index: 188799 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1016586 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4237. Min Act: -0.0000

Data Index: 75529 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4375. Min Act: -0.0000

Data Index: 354582 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4859. Min Act: -0.0000

Data Index: 846664 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4654. Min Act: -0.0000

Data Index: 746678 (C4 (Web Text))

Max Activating Token Index: 397