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

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

Neuron 5770 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3827. Min Act: -0.0000

Data Index: 354431 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3928. Min Act: -0.0000

Data Index: 300738 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3267. Min Act: -0.0000

Data Index: 1358649 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3453. Min Act: -0.0000

Data Index: 842685 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3382. Min Act: -0.0000

Data Index: 803694 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3544. Min Act: -0.0000

Data Index: 318981 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3197. Min Act: -0.0000

Data Index: 164066 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3451. Min Act: -0.0000

Data Index: 769964 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3141. Min Act: -0.0000

Data Index: 940144 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3175. Min Act: -0.0000

Data Index: 152583 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2984. Min Act: -0.0000

Data Index: 703066 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3084. Min Act: -0.0000

Data Index: 963902 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2977. Min Act: -0.0000

Data Index: 897638 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2701. Min Act: -0.0000

Data Index: 451389 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3037. Min Act: -0.0000

Data Index: 111368 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2889. Min Act: -0.0000

Data Index: 581353 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2721. Min Act: -0.0000

Data Index: 41736 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2866. Min Act: -0.0000

Data Index: 745352 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.3028. Min Act: -0.0000

Data Index: 256057 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.3928. Min Range: -0.3928

Max Act: 0.2881. Min Act: -0.0000

Data Index: 659003 (C4 (Web Text))

Max Activating Token Index: 878