Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1036 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0825. Min Act: -0.0001

Data Index: 290656 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1304029 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0821. Min Act: -0.0001

Data Index: 473077 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0826. Min Act: -0.0001

Data Index: 1026886 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0795. Min Act: -0.0001

Data Index: 649833 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0001

Data Index: 96496 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0748. Min Act: -0.0001

Data Index: 959682 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0717. Min Act: -0.0001

Data Index: 680537 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0675. Min Act: -0.0001

Data Index: 148827 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0823. Min Act: -0.0001

Data Index: 342316 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0627. Min Act: -0.0001

Data Index: 496705 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1019831 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0718. Min Act: -0.0001

Data Index: 261390 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0647. Min Act: -0.0001

Data Index: 342452 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0635. Min Act: -0.0001

Data Index: 535738 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0661. Min Act: -0.0001

Data Index: 566866 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1094594 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0755. Min Act: -0.0001

Data Index: 670897 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0652. Min Act: -0.0001

Data Index: 940648 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0644. Min Act: -0.0001

Data Index: 941452 (C4 (Web Text))

Max Activating Token Index: 84