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

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

Neuron 4599 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: 1.1137. Min Range: -1.1137

Max Act: 1.1137. Min Act: -0.0000

Data Index: 722003 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.1137. Min Range: -1.1137

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1205428 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9886. Min Act: -0.0000

Data Index: 758214 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1069460 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8722. Min Act: -0.0000

Data Index: 428823 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1058392 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8382. Min Act: -0.0000

Data Index: 701693 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8556. Min Act: -0.0000

Data Index: 97253 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8562. Min Act: -0.0000

Data Index: 322556 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8248. Min Act: -0.0000

Data Index: 356567 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8122. Min Act: -0.0000

Data Index: 58855 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.7559. Min Act: -0.0000

Data Index: 470629 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.7632. Min Act: -0.0000

Data Index: 679586 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1315181 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.8047. Min Act: -0.0000

Data Index: 504888 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.7329. Min Act: -0.0000

Data Index: 472290 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.7344. Min Act: -0.0000

Data Index: 589468 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1287172 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1211097 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 1.1137. Min Range: -1.1137

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1266220 (C4 (Web Text))

Max Activating Token Index: 48