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

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

Neuron 1600 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: 1.6795. Min Range: -1.6795

Max Act: 1.6795. Min Act: -0.0000

Data Index: 521179 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.5785. Min Act: -0.0000

Data Index: 920887 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.3420. Min Act: -0.0000

Data Index: 875254 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.5552. Min Act: -0.0000

Data Index: 457895 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.4697. Min Act: -0.0000

Data Index: 697093 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.3861. Min Act: -0.0000

Data Index: 310576 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.2512. Min Act: -0.0000

Data Index: 161797 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.3581. Min Act: -0.0000

Data Index: 45657 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.3130. Min Act: -0.0000

Data Index: 553114 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.2560. Min Act: -0.0000

Data Index: 908584 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.2811. Min Act: -0.0000

Data Index: 663174 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.1422. Min Act: -0.0000

Data Index: 408252 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.3092. Min Act: -0.0000

Data Index: 642065 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.2270. Min Act: -0.0000

Data Index: 709820 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.2618. Min Act: -0.0000

Data Index: 817278 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.1748. Min Act: -0.0000

Data Index: 71154 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.2409. Min Act: 0.0001

Data Index: 372445 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.1999. Min Act: -0.0000

Data Index: 826032 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.2132. Min Act: -0.0000

Data Index: 669371 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 1.6795. Min Range: -1.6795

Max Act: 1.1700. Min Act: -0.0000

Data Index: 1048701 (C4 (Web Text))

Max Activating Token Index: 974