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

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

Neuron 197 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0631. Min Range: -4.0631

Max Act: 4.0631. Min Act: -0.0000

Data Index: 522781 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.6455. Min Act: -0.0000

Data Index: 727832 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.6534. Min Act: -0.0000

Data Index: 1325061 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.7654. Min Act: -0.0000

Data Index: 891971 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.6878. Min Act: -0.0000

Data Index: 1313053 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.3562. Min Act: -0.0000

Data Index: 179237 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.6283. Min Act: -0.0000

Data Index: 956537 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.4982. Min Act: -0.0000

Data Index: 693046 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.5651. Min Act: -0.0000

Data Index: 1231707 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.3415. Min Act: -0.0000

Data Index: 81739 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.1416. Min Act: -0.0000

Data Index: 487752 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.1318. Min Act: -0.0000

Data Index: 413914 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 4.0631. Min Range: -4.0631

Max Act: 2.9737. Min Act: -0.0000

Data Index: 356530 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 4.0631. Min Range: -4.0631

Max Act: 3.1021. Min Act: -0.0000

Data Index: 343393 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 4.0631. Min Range: -4.0631

Max Act: 2.8964. Min Act: -0.0000

Data Index: 129149 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 4.0631. Min Range: -4.0631

Max Act: 2.9977. Min Act: -0.0000

Data Index: 1358042 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 4.0631. Min Range: -4.0631

Max Act: 2.7073. Min Act: -0.0000

Data Index: 441864 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 4.0631. Min Range: -4.0631

Max Act: 2.9380. Min Act: -0.0000

Data Index: 274140 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 4.0631. Min Range: -4.0631

Max Act: 2.8165. Min Act: -0.0000

Data Index: 1229916 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 4.0631. Min Range: -4.0631

Max Act: 2.8932. Min Act: -0.0000

Data Index: 807712 (C4 (Web Text))

Max Activating Token Index: 141