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

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

Neuron 5721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0164. Min Range: -1.0164

Max Act: 1.0164. Min Act: -0.0000

Data Index: 495187 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.9057. Min Act: -0.0000

Data Index: 51101 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.8052. Min Act: -0.0000

Data Index: 555719 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.7982. Min Act: -0.0000

Data Index: 566326 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1060002 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.7479. Min Act: -0.0000

Data Index: 993165 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.6131. Min Act: -0.0000

Data Index: 844725 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.6444. Min Act: -0.0000

Data Index: 824379 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.6307. Min Act: -0.0000

Data Index: 601190 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.6223. Min Act: -0.0000

Data Index: 767067 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1134837 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.6321. Min Act: -0.0000

Data Index: 806619 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5775. Min Act: -0.0000

Data Index: 611574 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5894. Min Act: -0.0000

Data Index: 858536 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5695. Min Act: -0.0000

Data Index: 558136 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5544. Min Act: -0.0000

Data Index: 108448 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5332. Min Act: -0.0000

Data Index: 905227 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5848. Min Act: -0.0000

Data Index: 521636 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5278. Min Act: -0.0000

Data Index: 586663 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.0164. Min Range: -1.0164

Max Act: 0.5066. Min Act: -0.0000

Data Index: 333464 (C4 (Web Text))

Max Activating Token Index: 75