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

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

Neuron 876 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.9160. Min Act: -0.0000

Data Index: 375726 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.5973. Min Act: -0.0000

Data Index: 361372 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.5063. Min Act: -0.0000

Data Index: 1208527 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.3516. Min Act: -0.0000

Data Index: 1026656 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1216376 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.3110. Min Act: -0.0000

Data Index: 247013 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2857. Min Act: -0.0000

Data Index: 359177 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.3636. Min Act: -0.0000

Data Index: 372788 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2592. Min Act: -0.0000

Data Index: 352116 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1234209 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2016. Min Act: -0.0000

Data Index: 653656 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2055. Min Act: -0.0000

Data Index: 1048087 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2001. Min Act: -0.0000

Data Index: 502060 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2741. Min Act: -0.0000

Data Index: 758138 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.0983. Min Act: -0.0000

Data Index: 379360 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.0847. Min Act: -0.0000

Data Index: 251193 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1014826 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.1494. Min Act: -0.0000

Data Index: 787646 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.0752. Min Act: -0.0000

Data Index: 733203 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 1.9160. Min Range: -1.9160

Max Act: 1.1801. Min Act: -0.0000

Data Index: 75637 (C4 (Web Text))

Max Activating Token Index: 547