Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 518 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0947. Min Act: -0.0001

Data Index: 553352 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0932. Min Act: -0.0001

Data Index: 118066 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0888. Min Act: -0.0001

Data Index: 14125 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0911. Min Act: -0.0001

Data Index: 862124 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0902. Min Act: -0.0001

Data Index: 432893 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0927. Min Act: -0.0001

Data Index: 56330 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1074410 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0922. Min Act: -0.0001

Data Index: 137510 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0899. Min Act: -0.0001

Data Index: 892763 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1240588 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1269173 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0951. Min Act: -0.0001

Data Index: 1065301 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0848. Min Act: -0.0001

Data Index: 178000 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0868. Min Act: -0.0001

Data Index: 694902 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0863. Min Act: -0.0001

Data Index: 686772 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0835. Min Act: -0.0001

Data Index: 1305657 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0858. Min Act: -0.0001

Data Index: 338002 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0827. Min Act: -0.0001

Data Index: 758112 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0809. Min Act: -0.0001

Data Index: 542137 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.0951. Min Range: -0.0951

Max Act: 0.0764. Min Act: -0.0001

Data Index: 39441 (C4 (Web Text))

Max Activating Token Index: 831