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

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

Neuron 3825 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: 1.2149. Min Range: -1.2149

Max Act: 1.2149. Min Act: -0.0001

Data Index: 1222240 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.1811. Min Act: -0.0001

Data Index: 105758 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.1257. Min Act: -0.0001

Data Index: 457722 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.1080. Min Act: -0.0001

Data Index: 612776 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0841. Min Act: -0.0001

Data Index: 1223405 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0329. Min Act: -0.0001

Data Index: 648154 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0819. Min Act: -0.0001

Data Index: 995866 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0427. Min Act: -0.0001

Data Index: 656708 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.1202. Min Act: -0.0001

Data Index: 631047 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0377. Min Act: -0.0001

Data Index: 1137680 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0183. Min Act: -0.0001

Data Index: 189941 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0014. Min Act: -0.0001

Data Index: 134270 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0394. Min Act: -0.0001

Data Index: 67200 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.2149. Min Range: -1.2149

Max Act: 0.9686. Min Act: -0.0001

Data Index: 1151599 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.2149. Min Range: -1.2149

Max Act: 0.9510. Min Act: -0.0001

Data Index: 161090 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.2149. Min Range: -1.2149

Max Act: 0.9838. Min Act: -0.0001

Data Index: 217968 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 1.2149. Min Range: -1.2149

Max Act: 0.9632. Min Act: -0.0001

Data Index: 315137 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 1.2149. Min Range: -1.2149

Max Act: 1.0072. Min Act: -0.0001

Data Index: 88603 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 1.2149. Min Range: -1.2149

Max Act: 0.9644. Min Act: -0.0001

Data Index: 434499 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 1.2149. Min Range: -1.2149

Max Act: 0.8656. Min Act: -0.0001

Data Index: 1287659 (C4 (Web Text))

Max Activating Token Index: 109