Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0002

Data Index: 817749 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0928. Min Act: -0.0002

Data Index: 287654 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1309709 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0932. Min Act: -0.0002

Data Index: 638300 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0935. Min Act: -0.0002

Data Index: 891478 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0936. Min Act: -0.0002

Data Index: 761159 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0901. Min Act: -0.0002

Data Index: 119091 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0891. Min Act: -0.0002

Data Index: 186673 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1080039 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1330831 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0867. Min Act: -0.0002

Data Index: 104980 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0830. Min Act: -0.0002

Data Index: 382144 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0825. Min Act: -0.0002

Data Index: 49731 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0873. Min Act: -0.0002

Data Index: 62975 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1153253 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0844. Min Act: -0.0002

Data Index: 753260 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0841. Min Act: -0.0002

Data Index: 892747 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0798. Min Act: -0.0002

Data Index: 736107 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0833. Min Act: -0.0002

Data Index: 643166 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0863. Min Act: -0.0002

Data Index: 237493 (C4 (Web Text))

Max Activating Token Index: 200