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

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

Neuron 4523 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0002

Data Index: 822802 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1173779 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0982. Min Act: -0.0002

Data Index: 403715 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0860. Min Act: -0.0002

Data Index: 819356 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1046. Min Act: -0.0002

Data Index: 142053 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0950. Min Act: -0.0002

Data Index: 258780 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0976. Min Act: -0.0002

Data Index: 837556 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0789. Min Act: -0.0002

Data Index: 208751 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1057. Min Act: -0.0002

Data Index: 824455 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1276997 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1027519 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1033848 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0944. Min Act: -0.0002

Data Index: 676733 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0936. Min Act: -0.0002

Data Index: 296619 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0899. Min Act: -0.0002

Data Index: 364655 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0772. Min Act: -0.0002

Data Index: 687450 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1056304 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0922. Min Act: -0.0002

Data Index: 729412 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0930. Min Act: -0.0002

Data Index: 615548 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0943. Min Act: -0.0002

Data Index: 415334 (C4 (Web Text))

Max Activating Token Index: 159