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

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

Neuron 2410 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1512. Min Act: -0.0001

Data Index: 975259 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1302507 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1231. Min Act: -0.0002

Data Index: 95701 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1082. Min Act: -0.0001

Data Index: 321372 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1090. Min Act: -0.0001

Data Index: 239234 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1013. Min Act: -0.0001

Data Index: 784212 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1049. Min Act: -0.0001

Data Index: 445127 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1349911 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0937. Min Act: -0.0001

Data Index: 622750 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1031. Min Act: -0.0001

Data Index: 362264 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1056135 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1351348 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0890. Min Act: -0.0002

Data Index: 364302 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0932. Min Act: -0.0002

Data Index: 417822 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1053653 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0908. Min Act: -0.0001

Data Index: 709910 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0928. Min Act: -0.0002

Data Index: 372285 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0866. Min Act: -0.0001

Data Index: 58028 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0936. Min Act: -0.0001

Data Index: 763690 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0846. Min Act: -0.0001

Data Index: 44551 (C4 (Web Text))

Max Activating Token Index: 261