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

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

Neuron 1273 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.9358. Min Act: -0.0001

Data Index: 120696 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.8147. Min Act: -0.0001

Data Index: 112229 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6153. Min Act: -0.0001

Data Index: 454736 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6018. Min Act: -0.0001

Data Index: 955578 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.6520. Min Act: -0.0001

Data Index: 849209 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.9465. Min Act: -0.0001

Data Index: 1338674 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.7599. Min Act: -0.0001

Data Index: 1162682 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.4856. Min Act: -0.0001

Data Index: 862874 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.3282. Min Act: -0.0001

Data Index: 915569 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.2802. Min Act: -0.0001

Data Index: 261584 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.5318. Min Act: -0.0001

Data Index: 316916 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.2265. Min Act: -0.0001

Data Index: 764505 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.4904. Min Act: -0.0001

Data Index: 1095413 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.1766. Min Act: -0.0001

Data Index: 1015201 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.1660. Min Act: -0.0001

Data Index: 243318 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.3174. Min Act: -0.0001

Data Index: 527522 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.2938. Min Act: -0.0001

Data Index: 17295 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.1259. Min Act: -0.0001

Data Index: 1131887 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.2692. Min Act: -0.0001

Data Index: 248156 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 3.9465. Min Range: -3.9465

Max Act: 3.2661. Min Act: -0.0001

Data Index: 1189761 (C4 (Web Text))

Max Activating Token Index: 962