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

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

Neuron 1525 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: 1.2790. Min Range: -1.2790

Max Act: 1.2790. Min Act: -0.0001

Data Index: 662385 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.2790. Min Range: -1.2790

Max Act: 1.0944. Min Act: -0.0001

Data Index: 60683 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8789. Min Act: -0.0001

Data Index: 107722 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9547. Min Act: -0.0001

Data Index: 973209 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.7191. Min Act: -0.0001

Data Index: 801803 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.7322. Min Act: -0.0001

Data Index: 903178 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9803. Min Act: -0.0001

Data Index: 712819 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.9776. Min Act: -0.0001

Data Index: 151377 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8937. Min Act: -0.0001

Data Index: 144118 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.5871. Min Act: -0.0001

Data Index: 691098 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8602. Min Act: -0.0001

Data Index: 1130834 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.7804. Min Act: -0.0001

Data Index: 607431 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8672. Min Act: -0.0001

Data Index: 87534 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8688. Min Act: -0.0001

Data Index: 505532 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8104. Min Act: -0.0001

Data Index: 692922 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.7744. Min Act: -0.0001

Data Index: 25428 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8009. Min Act: -0.0001

Data Index: 1250894 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8498. Min Act: -0.0001

Data Index: 1348255 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.8382. Min Act: -0.0001

Data Index: 990083 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 1.2790. Min Range: -1.2790

Max Act: 0.7972. Min Act: -0.0001

Data Index: 812558 (C4 (Web Text))

Max Activating Token Index: 940