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

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

Neuron 4058 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: 0.0957. Min Range: -0.0957

Max Act: 0.0874. Min Act: -0.0001

Data Index: 98219 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0957. Min Act: -0.0001

Data Index: 870713 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1115494 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1209034 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0869. Min Act: -0.0001

Data Index: 142075 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0833. Min Act: -0.0001

Data Index: 568306 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0900. Min Act: -0.0001

Data Index: 578069 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0922. Min Act: -0.0001

Data Index: 220952 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0796. Min Act: -0.0001

Data Index: 231574 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0831. Min Act: -0.0001

Data Index: 66997 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0798. Min Act: -0.0001

Data Index: 435104 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1079036 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1185714 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0687. Min Act: -0.0001

Data Index: 264784 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0699. Min Act: -0.0001

Data Index: 921275 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0756. Min Act: -0.0001

Data Index: 879124 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0751. Min Act: -0.0001

Data Index: 868383 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1008530 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0596. Min Act: -0.0001

Data Index: 947397 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0747. Min Act: -0.0001

Data Index: 1165395 (C4 (Web Text))

Max Activating Token Index: 806