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

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

Neuron 563 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8742. Min Act: -0.0000

Data Index: 644783 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8408. Min Act: -0.0000

Data Index: 436254 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8168. Min Act: -0.0000

Data Index: 824043 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8127. Min Act: -0.0000

Data Index: 187922 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1335674 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1151419 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7889. Min Act: -0.0000

Data Index: 738419 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1220289 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1237736 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7576. Min Act: -0.0000

Data Index: 410435 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7397. Min Act: -0.0000

Data Index: 8431 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7572. Min Act: -0.0000

Data Index: 47777 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7072. Min Act: -0.0000

Data Index: 474623 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7246. Min Act: -0.0000

Data Index: 881217 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7113. Min Act: -0.0000

Data Index: 166822 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7109. Min Act: -0.0000

Data Index: 310431 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6864. Min Act: -0.0000

Data Index: 962560 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6829. Min Act: -0.0000

Data Index: 692011 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6934. Min Act: -0.0000

Data Index: 215133 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6649. Min Act: -0.0000

Data Index: 759531 (C4 (Web Text))

Max Activating Token Index: 444