Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1378 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0002

Data Index: 528984 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0916. Min Act: -0.0002

Data Index: 582324 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1079681 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0900. Min Act: -0.0002

Data Index: 548880 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0888. Min Act: -0.0002

Data Index: 506754 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1105757 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0876. Min Act: -0.0002

Data Index: 420242 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0867. Min Act: -0.0002

Data Index: 424148 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0842. Min Act: -0.0002

Data Index: 5440 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1303146 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1178064 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0803. Min Act: -0.0002

Data Index: 833378 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0867. Min Act: -0.0002

Data Index: 564464 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0845. Min Act: -0.0002

Data Index: 58940 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0834. Min Act: -0.0002

Data Index: 807343 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0857. Min Act: -0.0002

Data Index: 752085 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0784. Min Act: -0.0002

Data Index: 99554 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0839. Min Act: -0.0002

Data Index: 973982 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0819. Min Act: -0.0002

Data Index: 359799 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0834. Min Act: -0.0002

Data Index: 79182 (C4 (Web Text))

Max Activating Token Index: 958