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

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

Neuron 2487 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.5768. Min Act: -0.0000

Data Index: 1220464 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.5655. Min Act: -0.0000

Data Index: 471551 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.3692. Min Act: -0.0000

Data Index: 345057 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.2731. Min Act: -0.0000

Data Index: 633060 (C4 (Web Text))

Max Activating Token Index: 640

Text #4

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.0844. Min Act: -0.0000

Data Index: 579572 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.1882. Min Act: -0.0000

Data Index: 971917 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.1417. Min Act: -0.0000

Data Index: 499540 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.2634. Min Act: -0.0000

Data Index: 952578 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.1118. Min Act: -0.0000

Data Index: 320719 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9325. Min Act: -0.0000

Data Index: 1127773 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.5768. Min Range: -2.5768

Max Act: 2.1163. Min Act: -0.0000

Data Index: 4505 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9922. Min Act: -0.0000

Data Index: 859356 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9987. Min Act: -0.0000

Data Index: 1001996 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.8248. Min Act: -0.0000

Data Index: 360797 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.8038. Min Act: -0.0000

Data Index: 593725 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.8785. Min Act: -0.0000

Data Index: 504188 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.6634. Min Act: -0.0000

Data Index: 122934 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.7466. Min Act: -0.0000

Data Index: 533579 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.6919. Min Act: -0.0000

Data Index: 426091 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 2.5768. Min Range: -2.5768

Max Act: 1.9144. Min Act: -0.0000

Data Index: 845803 (C4 (Web Text))

Max Activating Token Index: 264