Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2668 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1193. Min Act: -0.0001

Data Index: 729322 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1016423 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1316306 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1060384 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0918. Min Act: -0.0001

Data Index: 715063 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0946. Min Act: -0.0001

Data Index: 1228591 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0932. Min Act: -0.0001

Data Index: 223906 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1002572 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0841. Min Act: -0.0001

Data Index: 123715 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1191696 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1281621 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0855. Min Act: -0.0001

Data Index: 243962 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0806. Min Act: -0.0001

Data Index: 536629 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1244241 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0824. Min Act: -0.0001

Data Index: 272809 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0735. Min Act: -0.0001

Data Index: 114065 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1154542 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0803. Min Act: -0.0001

Data Index: 788387 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0774. Min Act: -0.0001

Data Index: 235368 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.1193. Min Range: -0.1193

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1153828 (C4 (Web Text))

Max Activating Token Index: 338