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

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

Neuron 3373 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: 1.9014. Min Range: -1.9014

Max Act: 1.9014. Min Act: -0.0001

Data Index: 1055825 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.6045. Min Act: -0.0001

Data Index: 525693 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.4974. Min Act: -0.0001

Data Index: 29436 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3960. Min Act: -0.0001

Data Index: 456483 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3616. Min Act: -0.0001

Data Index: 81124 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3512. Min Act: -0.0001

Data Index: 836154 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3549. Min Act: -0.0001

Data Index: 361607 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3417. Min Act: -0.0001

Data Index: 1523 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2872. Min Act: -0.0001

Data Index: 210976 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2476. Min Act: -0.0001

Data Index: 481161 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3057. Min Act: -0.0001

Data Index: 963796 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3529. Min Act: -0.0001

Data Index: 379466 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2852. Min Act: -0.0001

Data Index: 334222 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.1447. Min Act: -0.0001

Data Index: 66510 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2249. Min Act: -0.0001

Data Index: 781091 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2949. Min Act: -0.0001

Data Index: 652901 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2564. Min Act: -0.0001

Data Index: 404214 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.3448. Min Act: -0.0001

Data Index: 917362 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2233. Min Act: -0.0001

Data Index: 1170783 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.9014. Min Range: -1.9014

Max Act: 1.2851. Min Act: -0.0001

Data Index: 1071404 (C4 (Web Text))

Max Activating Token Index: 838