Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 803 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9731. Min Act: -0.0001

Data Index: 230884 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.9397. Min Act: -0.0001

Data Index: 963878 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8391. Min Act: -0.0001

Data Index: 762574 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8429. Min Act: -0.0001

Data Index: 725144 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7858. Min Act: -0.0001

Data Index: 1344877 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7634. Min Act: -0.0001

Data Index: 1325168 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7908. Min Act: -0.0001

Data Index: 1323332 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.8018. Min Act: -0.0001

Data Index: 458724 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7524. Min Act: -0.0001

Data Index: 1193027 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7397. Min Act: -0.0001

Data Index: 112530 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7735. Min Act: -0.0001

Data Index: 210272 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7294. Min Act: -0.0001

Data Index: 97415 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7456. Min Act: -0.0001

Data Index: 33005 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7449. Min Act: -0.0001

Data Index: 457291 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7423. Min Act: -0.0001

Data Index: 999624 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.6927. Min Act: -0.0001

Data Index: 936747 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7563. Min Act: -0.0001

Data Index: 699544 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.6842. Min Act: -0.0001

Data Index: 118493 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.6852. Min Act: -0.0001

Data Index: 827728 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.9731. Min Range: -0.9731

Max Act: 0.7476. Min Act: -0.0001

Data Index: 682931 (C4 (Web Text))

Max Activating Token Index: 460