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

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

Neuron 1726 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: 1.7377. Min Range: -1.7377

Max Act: 1.7377. Min Act: -0.0000

Data Index: 298452 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.5948. Min Act: -0.0000

Data Index: 181900 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.6764. Min Act: -0.0000

Data Index: 219430 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.3233. Min Act: -0.0000

Data Index: 326864 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.2672. Min Act: -0.0000

Data Index: 498277 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.1934. Min Act: -0.0000

Data Index: 928703 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.1530. Min Act: -0.0000

Data Index: 537844 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.0638. Min Act: -0.0000

Data Index: 882074 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.0707. Min Act: -0.0000

Data Index: 825055 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1184380 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1023370 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9821. Min Act: -0.0000

Data Index: 940375 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9331. Min Act: -0.0000

Data Index: 501764 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9462. Min Act: -0.0000

Data Index: 75066 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9603. Min Act: -0.0000

Data Index: 596894 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.7377. Min Range: -1.7377

Max Act: 1.0173. Min Act: -0.0000

Data Index: 79611 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1070747 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9043. Min Act: -0.0000

Data Index: 758618 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9307. Min Act: -0.0000

Data Index: 932484 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.7377. Min Range: -1.7377

Max Act: 0.9535. Min Act: -0.0000

Data Index: 446979 (C4 (Web Text))

Max Activating Token Index: 916