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

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

Neuron 479 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7404. Min Range: -3.7404

Max Act: 3.4440. Min Act: -0.0000

Data Index: 1091638 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 3.7404. Min Range: -3.7404

Max Act: 3.7404. Min Act: -0.0000

Data Index: 307315 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 3.7404. Min Range: -3.7404

Max Act: 3.3828. Min Act: -0.0000

Data Index: 1058317 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 3.7404. Min Range: -3.7404

Max Act: 3.6607. Min Act: -0.0001

Data Index: 1324772 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 3.7404. Min Range: -3.7404

Max Act: 3.0767. Min Act: -0.0000

Data Index: 748591 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 3.7404. Min Range: -3.7404

Max Act: 3.0679. Min Act: -0.0000

Data Index: 1210598 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 3.7404. Min Range: -3.7404

Max Act: 3.0206. Min Act: -0.0000

Data Index: 516545 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.9973. Min Act: -0.0000

Data Index: 129341 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.9384. Min Act: -0.0000

Data Index: 831177 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.8454. Min Act: -0.0000

Data Index: 819581 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.7134. Min Act: -0.0000

Data Index: 288945 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.7101. Min Act: -0.0000

Data Index: 894722 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.9910. Min Act: -0.0000

Data Index: 528691 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.7047. Min Act: -0.0000

Data Index: 930414 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.6987. Min Act: -0.0000

Data Index: 986166 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.8270. Min Act: -0.0000

Data Index: 370060 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.7917. Min Act: -0.0001

Data Index: 1132777 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.8458. Min Act: -0.0000

Data Index: 483555 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.7851. Min Act: -0.0000

Data Index: 1054779 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 3.7404. Min Range: -3.7404

Max Act: 2.6102. Min Act: -0.0000

Data Index: 939402 (C4 (Web Text))

Max Activating Token Index: 19