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

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

Neuron 605 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.1872. Min Range: -10.1872

Max Act: 10.1872. Min Act: -0.0000

Data Index: 1290887 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 10.1872. Min Range: -10.1872

Max Act: 9.3367. Min Act: -0.0000

Data Index: 431385 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 10.1872. Min Range: -10.1872

Max Act: 9.7809. Min Act: -0.0000

Data Index: 791964 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 10.1872. Min Range: -10.1872

Max Act: 9.2465. Min Act: -0.0000

Data Index: 697991 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 10.1872. Min Range: -10.1872

Max Act: 9.1911. Min Act: -0.0000

Data Index: 517197 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 10.1872. Min Range: -10.1872

Max Act: 9.4789. Min Act: -0.0000

Data Index: 1054984 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 10.1872. Min Range: -10.1872

Max Act: 8.5880. Min Act: 0.0001

Data Index: 796837 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 10.1872. Min Range: -10.1872

Max Act: 8.5848. Min Act: -0.0000

Data Index: 769087 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 10.1872. Min Range: -10.1872

Max Act: 7.7587. Min Act: 0.0000

Data Index: 348927 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 10.1872. Min Range: -10.1872

Max Act: 6.5701. Min Act: -0.0000

Data Index: 417008 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 10.1872. Min Range: -10.1872

Max Act: 7.7705. Min Act: 0.0000

Data Index: 22861 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 10.1872. Min Range: -10.1872

Max Act: 5.4171. Min Act: 0.0000

Data Index: 39067 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 10.1872. Min Range: -10.1872

Max Act: 5.6773. Min Act: 0.0001

Data Index: 65917 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 10.1872. Min Range: -10.1872

Max Act: 5.8035. Min Act: -0.0000

Data Index: 444214 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 10.1872. Min Range: -10.1872

Max Act: 4.7908. Min Act: -0.0000

Data Index: 1226635 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 10.1872. Min Range: -10.1872

Max Act: 6.3556. Min Act: 0.0000

Data Index: 21268 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 10.1872. Min Range: -10.1872

Max Act: 6.4520. Min Act: 0.0000

Data Index: 526965 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 10.1872. Min Range: -10.1872

Max Act: 5.6236. Min Act: 0.0000

Data Index: 1041070 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 10.1872. Min Range: -10.1872

Max Act: 5.2861. Min Act: 0.0001

Data Index: 968931 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 10.1872. Min Range: -10.1872

Max Act: 5.4269. Min Act: 0.0001

Data Index: 259602 (C4 (Web Text))

Max Activating Token Index: 927