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

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

Neuron 4788 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8175. Min Range: -5.8175

Max Act: 5.8175. Min Act: -0.0000

Data Index: 795822 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.9725. Min Act: -0.0000

Data Index: 344831 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.9413. Min Act: -0.0000

Data Index: 917906 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.9770. Min Act: -0.0000

Data Index: 1332738 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.8979. Min Act: -0.0000

Data Index: 119564 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.8501. Min Act: -0.0000

Data Index: 1218513 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.4008. Min Act: -0.0000

Data Index: 397389 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.7623. Min Act: -0.0000

Data Index: 842915 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.5398. Min Act: -0.0000

Data Index: 425212 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.8890. Min Act: -0.0000

Data Index: 77575 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.4913. Min Act: -0.0000

Data Index: 573659 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.4698. Min Act: -0.0000

Data Index: 1182212 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.1142. Min Act: -0.0000

Data Index: 1199860 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.4443. Min Act: -0.0000

Data Index: 182197 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.4011. Min Act: -0.0000

Data Index: 81417 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.3495. Min Act: -0.0000

Data Index: 1287951 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.4888. Min Act: -0.0000

Data Index: 866097 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 5.8175. Min Range: -5.8175

Max Act: 3.7741. Min Act: -0.0000

Data Index: 1038213 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.3145. Min Act: -0.0000

Data Index: 805759 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 5.8175. Min Range: -5.8175

Max Act: 4.2882. Min Act: -0.0000

Data Index: 1235150 (C4 (Web Text))

Max Activating Token Index: 464