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

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

Neuron 567 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1454116 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1400307 (Python Code)

Max Activating Token Index: 579

Text #2

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1388607 (Python Code)

Max Activating Token Index: 970

Text #3

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0933. Min Act: -0.0003

Data Index: 855356 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0920. Min Act: -0.0003

Data Index: 288519 (C4 (Web Text))

Max Activating Token Index: 471

Text #5

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1441926 (Python Code)

Max Activating Token Index: 636

Text #6

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0875. Min Act: -0.0002

Data Index: 253549 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0829. Min Act: -0.0002

Data Index: 725505 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1557914 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1498462 (Python Code)

Max Activating Token Index: 526

Text #10

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1384637 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1441082 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1572011 (Python Code)

Max Activating Token Index: 713

Text #13

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1405460 (Python Code)

Max Activating Token Index: 912

Text #14

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1484923 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1492077 (Python Code)

Max Activating Token Index: 824

Text #16

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1490675 (Python Code)

Max Activating Token Index: 150

Text #17

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1504826 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0681. Min Act: -0.0002

Data Index: 97616 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1614204 (Python Code)

Max Activating Token Index: 944