Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2827 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9151. Min Act: -0.0003

Data Index: 1350870 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9689. Min Act: -0.0003

Data Index: 1238118 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9284. Min Act: -0.0003

Data Index: 1064726 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8453. Min Act: -0.0003

Data Index: 971867 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9796. Min Act: -0.0003

Data Index: 1271076 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8308. Min Act: -0.0004

Data Index: 1002041 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8053. Min Act: -0.0003

Data Index: 109094 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9570. Min Act: -0.0003

Data Index: 619462 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.9304. Min Act: -0.0003

Data Index: 302449 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7873. Min Act: -0.0003

Data Index: 1109627 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7885. Min Act: -0.0003

Data Index: 703448 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.6933. Min Act: -0.0003

Data Index: 1055751 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8786. Min Act: -0.0003

Data Index: 302353 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8014. Min Act: -0.0003

Data Index: 998226 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7761. Min Act: -0.0003

Data Index: 537495 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8957. Min Act: -0.0003

Data Index: 1352212 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7916. Min Act: -0.0003

Data Index: 1008135 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.7894. Min Act: -0.0003

Data Index: 896625 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8687. Min Act: -0.0003

Data Index: 1255643 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.9796. Min Range: -0.9796

Max Act: 0.8732. Min Act: -0.0003

Data Index: 673819 (C4 (Web Text))

Max Activating Token Index: 848