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

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

Neuron 5271 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5690. Min Range: -1.5690

Max Act: 1.5690. Min Act: 0.0000

Data Index: 305378 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 1.5690. Min Range: -1.5690

Max Act: 1.2323. Min Act: -0.0000

Data Index: 442620 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 1.5690. Min Range: -1.5690

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1219189 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 1.5690. Min Range: -1.5690

Max Act: 1.0097. Min Act: -0.0000

Data Index: 306934 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 1.5690. Min Range: -1.5690

Max Act: 1.0523. Min Act: -0.0000

Data Index: 374536 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 1.5690. Min Range: -1.5690

Max Act: 1.0026. Min Act: -0.0000

Data Index: 587679 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.9914. Min Act: -0.0000

Data Index: 135015 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.9346. Min Act: -0.0000

Data Index: 981987 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.8607. Min Act: -0.0000

Data Index: 275839 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.8695. Min Act: -0.0000

Data Index: 645492 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1635106 (Python Code)

Max Activating Token Index: 850

Text #11

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1412080 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1111784 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.8284. Min Act: -0.0000

Data Index: 448154 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.7953. Min Act: -0.0000

Data Index: 442912 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.7932. Min Act: -0.0000

Data Index: 20230 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1545792 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.7474. Min Act: -0.0000

Data Index: 623544 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.7385. Min Act: -0.0000

Data Index: 586052 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.5690. Min Range: -1.5690

Max Act: 0.7424. Min Act: -0.0000

Data Index: 276905 (C4 (Web Text))

Max Activating Token Index: 25