Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1357 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9932. Min Act: -0.0003

Data Index: 145284 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9761. Min Act: -0.0003

Data Index: 1047159 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7497. Min Act: -0.0003

Data Index: 566612 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7828. Min Act: -0.0003

Data Index: 286724 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7653. Min Act: -0.0003

Data Index: 767954 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7329. Min Act: -0.0003

Data Index: 1000059 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7552. Min Act: -0.0003

Data Index: 1319584 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7819. Min Act: -0.0003

Data Index: 28667 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7515. Min Act: -0.0003

Data Index: 142939 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7313. Min Act: -0.0003

Data Index: 1210621 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7037. Min Act: -0.0003

Data Index: 1163648 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.6832. Min Act: -0.0003

Data Index: 1183533 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7434. Min Act: -0.0003

Data Index: 136935 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7207. Min Act: -0.0003

Data Index: 1140243 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7224. Min Act: -0.0003

Data Index: 200918 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.6676. Min Act: -0.0003

Data Index: 308601 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7113. Min Act: -0.0003

Data Index: 711161 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7124. Min Act: -0.0003

Data Index: 1153582 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7109. Min Act: -0.0003

Data Index: 1119773 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.7802. Min Act: -0.0003

Data Index: 1243816 (C4 (Web Text))

Max Activating Token Index: 721