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

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

Neuron 4217 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.2584. Min Act: -0.0000

Data Index: 997754 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.0580. Min Act: -0.0000

Data Index: 225846 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.0425. Min Act: -0.0000

Data Index: 29360 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.2584. Min Range: -1.2584

Max Act: 1.0224. Min Act: -0.0000

Data Index: 942764 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.9666. Min Act: -0.0000

Data Index: 188314 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1002115 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.9194. Min Act: -0.0000

Data Index: 150379 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.9029. Min Act: -0.0000

Data Index: 956213 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1049777 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8823. Min Act: -0.0000

Data Index: 380590 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8810. Min Act: -0.0000

Data Index: 917581 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8522. Min Act: -0.0000

Data Index: 950066 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.9389. Min Act: -0.0000

Data Index: 217344 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8937. Min Act: -0.0000

Data Index: 493293 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1217298 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8478. Min Act: -0.0000

Data Index: 109813 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8711. Min Act: -0.0000

Data Index: 290412 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8410. Min Act: -0.0000

Data Index: 1098984 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8423. Min Act: -0.0000

Data Index: 603489 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 1.2584. Min Range: -1.2584

Max Act: 0.8786. Min Act: -0.0000

Data Index: 787644 (C4 (Web Text))

Max Activating Token Index: 600