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

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

Neuron 4313 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0022. Min Range: -1.0022

Max Act: 1.0022. Min Act: -0.0000

Data Index: 795269 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1217937 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1242014 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7503. Min Act: -0.0000

Data Index: 1120417 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7281. Min Act: -0.0000

Data Index: 19162 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7715. Min Act: -0.0000

Data Index: 128855 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1002969 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7414. Min Act: -0.0000

Data Index: 887084 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6624. Min Act: -0.0000

Data Index: 235360 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7231. Min Act: -0.0000

Data Index: 640284 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7378. Min Act: -0.0000

Data Index: 832479 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6591. Min Act: -0.0000

Data Index: 1228392 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6428. Min Act: -0.0000

Data Index: 260343 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7083. Min Act: -0.0000

Data Index: 835736 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6739. Min Act: -0.0000

Data Index: 220279 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6469. Min Act: -0.0000

Data Index: 990351 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6404. Min Act: -0.0000

Data Index: 426861 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7175. Min Act: -0.0000

Data Index: 130511 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1316875 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 1.0022. Min Range: -1.0022

Max Act: 0.7338. Min Act: -0.0000

Data Index: 843766 (C4 (Web Text))

Max Activating Token Index: 961