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

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

Neuron 3516 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: 0.7950. Min Range: -0.7950

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1178082 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.7260. Min Act: -0.0000

Data Index: 755256 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.6064. Min Act: -0.0000

Data Index: 621448 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5731. Min Act: -0.0000

Data Index: 131179 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5309. Min Act: -0.0000

Data Index: 951902 (C4 (Web Text))

Max Activating Token Index: 906

Text #5

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1112766 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1226646 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4590. Min Act: -0.0000

Data Index: 562750 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.5001. Min Act: -0.0000

Data Index: 991167 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3468. Min Act: -0.0000

Data Index: 885057 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4051. Min Act: -0.0000

Data Index: 5085 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3901. Min Act: -0.0000

Data Index: 111587 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.4122. Min Act: -0.0000

Data Index: 111551 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3553. Min Act: -0.0000

Data Index: 842494 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3507. Min Act: -0.0000

Data Index: 658960 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1133893 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1147813 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3453. Min Act: -0.0000

Data Index: 560121 (C4 (Web Text))

Max Activating Token Index: 429

Text #18

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3414. Min Act: -0.0000

Data Index: 352344 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.7950. Min Range: -0.7950

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1053062 (C4 (Web Text))

Max Activating Token Index: 644