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

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

Neuron 3631 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3802. Min Range: -2.3802

Max Act: 2.3802. Min Act: -0.0000

Data Index: 317329 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 2.3802. Min Range: -2.3802

Max Act: 2.1464. Min Act: -0.0000

Data Index: 641817 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.6920. Min Act: -0.0000

Data Index: 564961 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.6972. Min Act: -0.0000

Data Index: 649521 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.5340. Min Act: -0.0000

Data Index: 269597 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.5006. Min Act: -0.0000

Data Index: 1213579 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4797. Min Act: -0.0000

Data Index: 28714 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.3497. Min Act: -0.0000

Data Index: 1266251 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.3406. Min Act: -0.0000

Data Index: 477963 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4764. Min Act: -0.0000

Data Index: 178454 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4128. Min Act: -0.0000

Data Index: 115495 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.2356. Min Act: -0.0000

Data Index: 1340416 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4640. Min Act: -0.0000

Data Index: 756874 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.3768. Min Act: -0.0000

Data Index: 611941 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.3509. Min Act: -0.0000

Data Index: 1046161 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.3463. Min Act: -0.0000

Data Index: 380484 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4923. Min Act: -0.0000

Data Index: 383064 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.4031. Min Act: -0.0000

Data Index: 624398 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1279950 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 2.3802. Min Range: -2.3802

Max Act: 1.2833. Min Act: -0.0000

Data Index: 447875 (C4 (Web Text))

Max Activating Token Index: 945