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

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

Neuron 3647 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1268. Min Range: -1.1268

Max Act: 1.1268. Min Act: -0.0000

Data Index: 976595 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.9178. Min Act: -0.0000

Data Index: 814219 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8758. Min Act: -0.0000

Data Index: 800917 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8405. Min Act: -0.0000

Data Index: 653812 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1315034 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8403. Min Act: -0.0000

Data Index: 1347634 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7459. Min Act: -0.0000

Data Index: 797717 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8149. Min Act: -0.0000

Data Index: 107561 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7574. Min Act: -0.0000

Data Index: 293102 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7724. Min Act: -0.0000

Data Index: 62268 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1055751 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1077824 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1310706 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7810. Min Act: -0.0000

Data Index: 112958 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1049376 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1263372 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.6871. Min Act: -0.0000

Data Index: 226691 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.6503. Min Act: -0.0000

Data Index: 1161952 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1003867 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.1268. Min Range: -1.1268

Max Act: 0.6828. Min Act: -0.0000

Data Index: 993615 (C4 (Web Text))

Max Activating Token Index: 818