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

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

Neuron 5687 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: 1.5343. Min Range: -1.5343

Max Act: 1.2592. Min Act: -0.0000

Data Index: 1260310 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.5343. Min Act: -0.0000

Data Index: 810551 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.5270. Min Act: -0.0000

Data Index: 863218 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.3872. Min Act: -0.0000

Data Index: 1145622 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.3808. Min Act: -0.0000

Data Index: 126796 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1572827 (Python Code)

Max Activating Token Index: 1017

Text #6

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.2009. Min Act: -0.0000

Data Index: 901271 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1418719 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1380652 (Python Code)

Max Activating Token Index: 618

Text #9

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.1020. Min Act: -0.0000

Data Index: 1599966 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.3921. Min Act: -0.0000

Data Index: 845549 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1090800 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.2561. Min Act: -0.0000

Data Index: 1556106 (Python Code)

Max Activating Token Index: 664

Text #13

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.2052. Min Act: -0.0000

Data Index: 20231 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.2743. Min Act: -0.0000

Data Index: 18682 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.1406. Min Act: -0.0000

Data Index: 1481755 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.1833. Min Act: -0.0000

Data Index: 517651 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.2046. Min Act: -0.0000

Data Index: 1642849 (Python Code)

Max Activating Token Index: 546

Text #18

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.1393. Min Act: -0.0000

Data Index: 349104 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.5343. Min Range: -1.5343

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1006410 (C4 (Web Text))

Max Activating Token Index: 422