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

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

Neuron 1341 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1225759 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1109396 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3643. Min Act: -0.0000

Data Index: 617403 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3100. Min Act: -0.0000

Data Index: 946864 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1076499 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2906. Min Act: -0.0000

Data Index: 845623 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3136. Min Act: -0.0000

Data Index: 271319 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3042. Min Act: -0.0000

Data Index: 89975 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3119. Min Act: -0.0000

Data Index: 178243 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1312064 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1210279 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2898. Min Act: -0.0000

Data Index: 1311845 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1167736 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2979. Min Act: -0.0000

Data Index: 354112 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1316895 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2917. Min Act: -0.0000

Data Index: 158727 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2841. Min Act: -0.0000

Data Index: 913068 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2819. Min Act: -0.0000

Data Index: 279844 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2562. Min Act: -0.0000

Data Index: 815198 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.4100. Min Range: -0.4100

Max Act: 0.2809. Min Act: -0.0000

Data Index: 628756 (C4 (Web Text))

Max Activating Token Index: 359