Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1729 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 12.0534. Min Range: -12.0534

Max Act: 12.0534. Min Act: -0.0002

Data Index: 211581 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 12.0534. Min Range: -12.0534

Max Act: 10.5632. Min Act: -0.0002

Data Index: 657273 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 12.0534. Min Range: -12.0534

Max Act: 9.0270. Min Act: -0.0002

Data Index: 997359 (C4 (Web Text))

Max Activating Token Index: 115

Text #3

Max Range: 12.0534. Min Range: -12.0534

Max Act: 7.7185. Min Act: -0.0002

Data Index: 138609 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 12.0534. Min Range: -12.0534

Max Act: 7.5375. Min Act: -0.0002

Data Index: 439466 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 12.0534. Min Range: -12.0534

Max Act: 7.9067. Min Act: -0.0002

Data Index: 11873 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 12.0534. Min Range: -12.0534

Max Act: 8.1286. Min Act: -0.0002

Data Index: 921645 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 12.0534. Min Range: -12.0534

Max Act: 9.5768. Min Act: -0.0002

Data Index: 859067 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 12.0534. Min Range: -12.0534

Max Act: 0.9759. Min Act: -0.0002

Data Index: 138680 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 12.0534. Min Range: -12.0534

Max Act: 8.0249. Min Act: -0.0002

Data Index: 933974 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 12.0534. Min Range: -12.0534

Max Act: 8.9740. Min Act: -0.0002

Data Index: 684795 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 12.0534. Min Range: -12.0534

Max Act: 7.8975. Min Act: -0.0002

Data Index: 1232385 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 12.0534. Min Range: -12.0534

Max Act: 7.3222. Min Act: -0.0002

Data Index: 807801 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 12.0534. Min Range: -12.0534

Max Act: 7.8435. Min Act: -0.0002

Data Index: 913276 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 12.0534. Min Range: -12.0534

Max Act: 6.3509. Min Act: -0.0002

Data Index: 600357 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 12.0534. Min Range: -12.0534

Max Act: 6.6087. Min Act: -0.0002

Data Index: 34864 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 12.0534. Min Range: -12.0534

Max Act: 2.7268. Min Act: -0.0002

Data Index: 43929 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 12.0534. Min Range: -12.0534

Max Act: 7.6038. Min Act: -0.0002

Data Index: 626498 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 12.0534. Min Range: -12.0534

Max Act: 2.8608. Min Act: -0.0002

Data Index: 290273 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 12.0534. Min Range: -12.0534

Max Act: 3.2098. Min Act: -0.0002

Data Index: 1147692 (C4 (Web Text))

Max Activating Token Index: 628