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

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

Neuron 2475 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: 0.5639. Min Range: -0.5639

Max Act: 0.5583. Min Act: -0.0001

Data Index: 222766 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.5639. Min Act: -0.0001

Data Index: 1246093 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4860. Min Act: -0.0000

Data Index: 916512 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4962. Min Act: -0.0001

Data Index: 1257620 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4460. Min Act: -0.0001

Data Index: 49491 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4609. Min Act: -0.0000

Data Index: 682891 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4688. Min Act: -0.0000

Data Index: 536809 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4384. Min Act: -0.0000

Data Index: 18472 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1152853 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4782. Min Act: -0.0001

Data Index: 555874 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1191622 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4735. Min Act: -0.0000

Data Index: 111277 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.5045. Min Act: -0.0000

Data Index: 714113 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4855. Min Act: -0.0000

Data Index: 616574 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4833. Min Act: -0.0000

Data Index: 660852 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4783. Min Act: -0.0001

Data Index: 1344308 (C4 (Web Text))

Max Activating Token Index: 948

Text #17

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4794. Min Act: -0.0000

Data Index: 5360 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4767. Min Act: -0.0000

Data Index: 154048 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.5639. Min Range: -0.5639

Max Act: 0.4630. Min Act: -0.0000

Data Index: 98732 (C4 (Web Text))

Max Activating Token Index: 167