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

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

Neuron 3903 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.7561. Min Act: -0.0001

Data Index: 947003 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.6924. Min Act: -0.0001

Data Index: 171995 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1046712 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.6248. Min Act: -0.0001

Data Index: 565650 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.5000. Min Act: -0.0001

Data Index: 809555 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.6769. Min Act: -0.0001

Data Index: 773443 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.6280. Min Act: -0.0001

Data Index: 232125 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4784. Min Act: -0.0001

Data Index: 92370 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1228287 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.5650. Min Act: -0.0001

Data Index: 904883 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4982. Min Act: -0.0001

Data Index: 674796 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.6038. Min Act: -0.0001

Data Index: 275643 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4504. Min Act: -0.0001

Data Index: 467953 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4813. Min Act: -0.0001

Data Index: 503152 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.5416. Min Act: -0.0001

Data Index: 666293 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4853. Min Act: -0.0001

Data Index: 138705 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.5426. Min Act: -0.0001

Data Index: 801242 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4565. Min Act: -0.0001

Data Index: 729179 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4735. Min Act: -0.0001

Data Index: 751449 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.7561. Min Range: -0.7561

Max Act: 0.4608. Min Act: -0.0001

Data Index: 909118 (C4 (Web Text))

Max Activating Token Index: 208