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

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

Neuron 967 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: 772379 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0934. Min Act: -0.0002

Data Index: 478287 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0871. Min Act: -0.0002

Data Index: 222829 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1133202 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1286802 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0901. Min Act: -0.0002

Data Index: 611658 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0824. Min Act: -0.0002

Data Index: 656249 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0854. Min Act: -0.0002

Data Index: 290415 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0849. Min Act: -0.0002

Data Index: 599688 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0840. Min Act: -0.0002

Data Index: 657951 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0811. Min Act: -0.0002

Data Index: 145089 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1179224 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1117635 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0775. Min Act: -0.0002

Data Index: 288569 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0833. Min Act: -0.0002

Data Index: 109440 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0801. Min Act: -0.0002

Data Index: 810676 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1184208 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0770. Min Act: -0.0002

Data Index: 410369 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0794. Min Act: -0.0002

Data Index: 647608 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1126686 (C4 (Web Text))

Max Activating Token Index: 80