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

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

Neuron 91 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.0750. Min Act: 0.0000

Data Index: 214549 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8315. Min Act: -0.0000

Data Index: 669570 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1021312 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1347903 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1157741 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1005891 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8519. Min Act: -0.0000

Data Index: 146368 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7597. Min Act: -0.0000

Data Index: 435660 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7884. Min Act: -0.0000

Data Index: 325723 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7181. Min Act: -0.0000

Data Index: 115605 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1330918 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1216398 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1347281 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7206. Min Act: -0.0000

Data Index: 118289 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7639. Min Act: -0.0000

Data Index: 224150 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7414. Min Act: -0.0000

Data Index: 12680 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7623. Min Act: -0.0000

Data Index: 692608 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7044. Min Act: -0.0000

Data Index: 195556 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1210509 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.6678. Min Act: -0.0000

Data Index: 709184 (C4 (Web Text))

Max Activating Token Index: 32