Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 541 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.5690. Min Act: -0.0000

Data Index: 899500 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.2424. Min Act: -0.0000

Data Index: 142519 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.9846. Min Act: -0.0000

Data Index: 642678 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.8107. Min Act: -0.0000

Data Index: 1018844 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1282179 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 2.5690. Min Range: -2.5690

Max Act: 2.0284. Min Act: -0.0000

Data Index: 611874 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.8115. Min Act: -0.0000

Data Index: 387989 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.7827. Min Act: -0.0000

Data Index: 885837 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6245. Min Act: -0.0000

Data Index: 166928 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6653. Min Act: -0.0000

Data Index: 864296 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6404. Min Act: -0.0000

Data Index: 1105822 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.5896. Min Act: -0.0000

Data Index: 757412 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.5838. Min Act: -0.0000

Data Index: 905801 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.4951. Min Act: -0.0000

Data Index: 299771 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1117756 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6760. Min Act: -0.0000

Data Index: 95974 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6329. Min Act: -0.0000

Data Index: 1221549 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.5430. Min Act: -0.0000

Data Index: 390846 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.7090. Min Act: -0.0000

Data Index: 796547 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 2.5690. Min Range: -2.5690

Max Act: 1.6019. Min Act: -0.0001

Data Index: 868264 (C4 (Web Text))

Max Activating Token Index: 512