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

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

Neuron 293 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: 1.0058. Min Range: -1.0058

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1283804 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 1.0058. Min Range: -1.0058

Max Act: 1.0058. Min Act: -0.0000

Data Index: 335722 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.9119. Min Act: -0.0000

Data Index: 851148 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1290326 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.8001. Min Act: -0.0000

Data Index: 840810 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.8032. Min Act: -0.0000

Data Index: 365443 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7210. Min Act: -0.0000

Data Index: 878405 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1119784 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1086307 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.6199. Min Act: -0.0000

Data Index: 1330375 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.6299. Min Act: -0.0000

Data Index: 75902 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.6204. Min Act: -0.0000

Data Index: 345733 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5812. Min Act: -0.0000

Data Index: 643639 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5925. Min Act: -0.0000

Data Index: 434642 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5713. Min Act: -0.0000

Data Index: 439384 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1171382 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5688. Min Act: -0.0000

Data Index: 976231 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1119358 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5567. Min Act: -0.0000

Data Index: 846919 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 1.0058. Min Range: -1.0058

Max Act: 0.5004. Min Act: -0.0000

Data Index: 52493 (C4 (Web Text))

Max Activating Token Index: 564