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

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

Neuron 4752 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5966. Min Range: -1.5966

Max Act: 1.5966. Min Act: -0.0000

Data Index: 855461 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 1.5966. Min Range: -1.5966

Max Act: 1.1263. Min Act: -0.0000

Data Index: 696794 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.5966. Min Range: -1.5966

Max Act: 1.0342. Min Act: -0.0000

Data Index: 994244 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 1.5966. Min Range: -1.5966

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1055922 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.8984. Min Act: -0.0000

Data Index: 814606 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.8540. Min Act: -0.0000

Data Index: 513965 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.8567. Min Act: -0.0000

Data Index: 1040901 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.8192. Min Act: -0.0000

Data Index: 781340 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.7528. Min Act: -0.0000

Data Index: 493074 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.7899. Min Act: -0.0000

Data Index: 291685 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.7135. Min Act: -0.0000

Data Index: 482534 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.8000. Min Act: -0.0000

Data Index: 26943 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1192762 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1093465 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.7046. Min Act: -0.0000

Data Index: 623666 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.6735. Min Act: -0.0000

Data Index: 898177 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.8155. Min Act: -0.0000

Data Index: 255181 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.7037. Min Act: -0.0000

Data Index: 482649 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1057131 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 1.5966. Min Range: -1.5966

Max Act: 0.6351. Min Act: -0.0000

Data Index: 83635 (C4 (Web Text))

Max Activating Token Index: 296