Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 17 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.6907. Min Act: -0.0001

Data Index: 688467 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2243. Min Act: -0.0001

Data Index: 369511 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2293. Min Act: -0.0001

Data Index: 276399 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2362. Min Act: -0.0001

Data Index: 329633 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1986. Min Act: -0.0001

Data Index: 1010940 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1849. Min Act: -0.0001

Data Index: 881345 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1153. Min Act: -0.0001

Data Index: 196142 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.2539. Min Act: -0.0001

Data Index: 600465 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1917. Min Act: -0.0001

Data Index: 1210778 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1869. Min Act: -0.0001

Data Index: 1177339 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1186. Min Act: -0.0001

Data Index: 255951 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1198. Min Act: -0.0001

Data Index: 1048827 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.0744. Min Act: -0.0001

Data Index: 253598 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1055. Min Act: -0.0001

Data Index: 780156 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1051. Min Act: -0.0001

Data Index: 112436 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1109. Min Act: -0.0001

Data Index: 102129 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.0587. Min Act: -0.0001

Data Index: 1030715 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1577. Min Act: -0.0001

Data Index: 184231 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.1037. Min Act: -0.0001

Data Index: 1071502 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.6907. Min Range: -1.6907

Max Act: 1.0797. Min Act: -0.0001

Data Index: 1232446 (C4 (Web Text))

Max Activating Token Index: 130