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

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

Neuron 2804 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4925. Min Act: -0.0001

Data Index: 1265769 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4030. Min Act: -0.0001

Data Index: 414717 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1960. Min Act: -0.0001

Data Index: 1321780 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3289. Min Act: -0.0001

Data Index: 700379 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2036. Min Act: -0.0001

Data Index: 366280 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2866. Min Act: -0.0001

Data Index: 1142627 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1719. Min Act: -0.0001

Data Index: 1134682 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.3306. Min Act: -0.0001

Data Index: 1023217 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2216. Min Act: -0.0001

Data Index: 1033013 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2079. Min Act: -0.0001

Data Index: 1278608 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2700. Min Act: -0.0001

Data Index: 408092 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1114495 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0847. Min Act: -0.0001

Data Index: 129356 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0563. Min Act: -0.0001

Data Index: 257006 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0252. Min Act: -0.0001

Data Index: 1328623 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1040. Min Act: -0.0001

Data Index: 711485 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1092. Min Act: -0.0001

Data Index: 186242 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0615. Min Act: -0.0001

Data Index: 480821 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.4925. Min Range: -1.4925

Max Act: 0.9993. Min Act: -0.0001

Data Index: 181818 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1140. Min Act: -0.0001

Data Index: 154122 (C4 (Web Text))

Max Activating Token Index: 285