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

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

Neuron 4206 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0000

Data Index: 655285 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1147. Min Act: -0.0000

Data Index: 752112 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1184702 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1116123 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1080. Min Act: -0.0000

Data Index: 980110 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1063. Min Act: -0.0000

Data Index: 475819 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1163898 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1003. Min Act: -0.0000

Data Index: 934113 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1219039 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1292222 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0968. Min Act: -0.0000

Data Index: 327365 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0895. Min Act: -0.0000

Data Index: 705605 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1059990 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0914. Min Act: -0.0001

Data Index: 200141 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0870. Min Act: -0.0000

Data Index: 30255 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0882. Min Act: -0.0000

Data Index: 182020 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0815. Min Act: -0.0000

Data Index: 415379 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0896. Min Act: -0.0000

Data Index: 604517 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0803. Min Act: -0.0001

Data Index: 914470 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0858. Min Act: -0.0000

Data Index: 17600 (C4 (Web Text))

Max Activating Token Index: 942