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

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

Neuron 4753 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.3306. Min Act: -0.0000

Data Index: 1276324 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1354619 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0617. Min Act: -0.0000

Data Index: 798148 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0030. Min Act: -0.0000

Data Index: 882034 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9974. Min Act: -0.0000

Data Index: 845666 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9582. Min Act: -0.0000

Data Index: 667900 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9250. Min Act: -0.0000

Data Index: 818344 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1023380 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 1.3306. Min Range: -1.3306

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1332830 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1228393 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9067. Min Act: -0.0000

Data Index: 141998 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9030. Min Act: -0.0000

Data Index: 813684 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1186747 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.8509. Min Act: -0.0000

Data Index: 573429 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.9064. Min Act: -0.0000

Data Index: 562825 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.8489. Min Act: -0.0000

Data Index: 627070 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1003375 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.8335. Min Act: -0.0000

Data Index: 903189 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.8982. Min Act: -0.0000

Data Index: 659584 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.3306. Min Range: -1.3306

Max Act: 0.7879. Min Act: -0.0000

Data Index: 167168 (C4 (Web Text))

Max Activating Token Index: 370