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

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

Neuron 3866 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2836. Min Range: -2.2836

Max Act: 2.2836. Min Act: -0.0000

Data Index: 363502 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.6780. Min Act: -0.0000

Data Index: 144615 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.4318. Min Act: -0.0000

Data Index: 139360 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.2900. Min Act: -0.0000

Data Index: 367822 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.2262. Min Act: -0.0000

Data Index: 150540 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.2505. Min Act: -0.0000

Data Index: 270802 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.0690. Min Act: -0.0000

Data Index: 741807 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.1795. Min Act: -0.0000

Data Index: 619396 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1222925 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.0566. Min Act: -0.0000

Data Index: 189063 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.0542. Min Act: -0.0000

Data Index: 679843 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.0592. Min Act: -0.0000

Data Index: 927694 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.0344. Min Act: -0.0000

Data Index: 945504 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 2.2836. Min Range: -2.2836

Max Act: 0.9914. Min Act: -0.0000

Data Index: 323746 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.2836. Min Range: -2.2836

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1046182 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 2.2836. Min Range: -2.2836

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1266318 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 2.2836. Min Range: -2.2836

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1046444 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 2.2836. Min Range: -2.2836

Max Act: 0.9337. Min Act: -0.0000

Data Index: 824059 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 2.2836. Min Range: -2.2836

Max Act: 0.9178. Min Act: -0.0000

Data Index: 963266 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 2.2836. Min Range: -2.2836

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1138331 (C4 (Web Text))

Max Activating Token Index: 813