Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1361 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0004

Data Index: 655567 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1221. Min Act: -0.0004

Data Index: 902181 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1031. Min Act: -0.0004

Data Index: 656704 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0971. Min Act: -0.0004

Data Index: 613562 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0943. Min Act: -0.0004

Data Index: 810771 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0915. Min Act: -0.0004

Data Index: 5724 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0880. Min Act: -0.0004

Data Index: 403244 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0876. Min Act: -0.0004

Data Index: 1026099 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0884. Min Act: -0.0004

Data Index: 824025 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0855. Min Act: -0.0004

Data Index: 426182 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0863. Min Act: -0.0004

Data Index: 1309132 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0839. Min Act: -0.0004

Data Index: 53183 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0846. Min Act: -0.0004

Data Index: 343868 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0822. Min Act: -0.0004

Data Index: 486617 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0812. Min Act: -0.0004

Data Index: 186004 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0822. Min Act: -0.0004

Data Index: 468061 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0838. Min Act: -0.0004

Data Index: 310764 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0819. Min Act: -0.0004

Data Index: 873588 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0820. Min Act: -0.0004

Data Index: 1135043 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0832. Min Act: -0.0004

Data Index: 1326208 (C4 (Web Text))

Max Activating Token Index: 761