Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4203 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1003. Min Act: -0.0001

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1149. Min Act: -0.0001

Data Index: 271546 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1023. Min Act: -0.0001

Data Index: 824225 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0967. Min Act: -0.0001

Data Index: 499314 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0969. Min Act: -0.0001

Data Index: 816826 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1025. Min Act: -0.0001

Data Index: 621759 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1353494 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0898. Min Act: -0.0001

Data Index: 22776 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1344371 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1358810 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0891. Min Act: -0.0001

Data Index: 327576 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1196752 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0953. Min Act: -0.0001

Data Index: 947537 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1002100 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0879. Min Act: -0.0001

Data Index: 684630 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0855. Min Act: -0.0001

Data Index: 252499 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1183003 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0843. Min Act: -0.0001

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0843. Min Act: -0.0001

Data Index: 343181 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0838. Min Act: -0.0001

Data Index: 878725 (C4 (Web Text))

Max Activating Token Index: 536