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

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

Neuron 5901 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.8764. Min Act: -0.0000

Data Index: 1228410 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.5289. Min Act: -0.0000

Data Index: 1279102 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.6670. Min Act: -0.0000

Data Index: 635903 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.2384. Min Act: -0.0000

Data Index: 1165372 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.3307. Min Act: -0.0000

Data Index: 836704 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.1073. Min Act: -0.0000

Data Index: 618035 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.1634. Min Act: -0.0000

Data Index: 294415 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.8583. Min Act: -0.0000

Data Index: 1044232 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.9023. Min Act: -0.0000

Data Index: 324695 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.9832. Min Act: -0.0000

Data Index: 394240 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.9579. Min Act: -0.0000

Data Index: 363146 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.1208. Min Act: -0.0000

Data Index: 1004606 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.9564. Min Act: 0.0000

Data Index: 870357 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.8527. Min Act: -0.0000

Data Index: 1161903 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.8156. Min Act: -0.0000

Data Index: 908896 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.6345. Min Act: -0.0000

Data Index: 742151 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.5462. Min Act: 0.0000

Data Index: 102612 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 4.8764. Min Range: -4.8764

Max Act: 4.0406. Min Act: -0.0000

Data Index: 83000 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.3840. Min Act: -0.0000

Data Index: 872409 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 4.8764. Min Range: -4.8764

Max Act: 3.7007. Min Act: -0.0000

Data Index: 30696 (C4 (Web Text))

Max Activating Token Index: 498