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

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

Neuron 3353 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1132216 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 1.0626. Min Range: -1.0626

Max Act: 1.0626. Min Act: -0.0000

Data Index: 220456 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1204212 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8482. Min Act: -0.0000

Data Index: 114253 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.8640. Min Act: -0.0000

Data Index: 346836 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.7805. Min Act: -0.0000

Data Index: 651845 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.7184. Min Act: -0.0000

Data Index: 754507 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.7204. Min Act: -0.0000

Data Index: 749346 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1291498 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.7256. Min Act: -0.0000

Data Index: 70387 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6965. Min Act: -0.0000

Data Index: 863860 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6938. Min Act: -0.0000

Data Index: 801500 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6629. Min Act: -0.0000

Data Index: 937454 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1310615 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6445. Min Act: -0.0000

Data Index: 450759 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1252913 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6418. Min Act: -0.0000

Data Index: 256455 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6402. Min Act: -0.0000

Data Index: 63245 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6355. Min Act: -0.0000

Data Index: 94881 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 1.0626. Min Range: -1.0626

Max Act: 0.6212. Min Act: -0.0000

Data Index: 528855 (C4 (Web Text))

Max Activating Token Index: 622