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

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

Neuron 5828 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: 0.4851. Min Range: -0.4851

Max Act: 0.4851. Min Act: -0.0000

Data Index: 85096 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3465. Min Act: -0.0000

Data Index: 399593 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1353788 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1279549 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3560. Min Act: -0.0000

Data Index: 376815 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3172. Min Act: -0.0000

Data Index: 598854 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3354. Min Act: 0.0000

Data Index: 1124069 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1325554 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3335. Min Act: -0.0000

Data Index: 63950 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1037715 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2936. Min Act: -0.0000

Data Index: 1030027 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2816. Min Act: -0.0000

Data Index: 515432 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2889. Min Act: -0.0000

Data Index: 356477 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2829. Min Act: -0.0000

Data Index: 871901 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1354064 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1096067 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2894. Min Act: -0.0000

Data Index: 551904 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2791. Min Act: -0.0000

Data Index: 463153 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.3072. Min Act: -0.0000

Data Index: 247393 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 0.4851. Min Range: -0.4851

Max Act: 0.2878. Min Act: -0.0000

Data Index: 48809 (C4 (Web Text))

Max Activating Token Index: 38