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

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

Neuron 1411 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.6367. Min Act: -0.0001

Data Index: 1451393 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.5870. Min Act: -0.0001

Data Index: 1319704 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.8006. Min Act: -0.0001

Data Index: 1625827 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.2622. Min Act: -0.0001

Data Index: 1405332 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.3624. Min Act: -0.0001

Data Index: 1622570 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.3073. Min Act: -0.0001

Data Index: 584979 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.2599. Min Act: -0.0001

Data Index: 1210690 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.2394. Min Act: -0.0001

Data Index: 1389127 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.2962. Min Act: -0.0001

Data Index: 513839 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.2972. Min Act: -0.0001

Data Index: 913138 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.1583. Min Act: -0.0001

Data Index: 1508080 (Python Code)

Max Activating Token Index: 540

Text #11

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.3743. Min Act: -0.0001

Data Index: 1257608 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.1092. Min Act: -0.0001

Data Index: 686088 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.2289. Min Act: -0.0001

Data Index: 120483 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.1131. Min Act: -0.0001

Data Index: 115662 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.0635. Min Act: -0.0001

Data Index: 1557322 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.1959. Min Act: -0.0001

Data Index: 1285621 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.1703. Min Act: -0.0001

Data Index: 1384513 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.2434. Min Act: -0.0001

Data Index: 616077 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 1.8006. Min Range: -1.8006

Max Act: 1.0105. Min Act: -0.0001

Data Index: 1483200 (Python Code)

Max Activating Token Index: 266