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

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

Neuron 5229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1607. Min Range: -4.1607

Max Act: 4.1607. Min Act: -0.0000

Data Index: 1076730 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9748. Min Act: -0.0000

Data Index: 156195 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.9304. Min Act: -0.0000

Data Index: 698353 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.8888. Min Act: -0.0000

Data Index: 1178911 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.4705. Min Act: -0.0000

Data Index: 508857 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.4837. Min Act: -0.0000

Data Index: 611327 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.2006. Min Act: -0.0000

Data Index: 129544 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.9163. Min Act: -0.0000

Data Index: 1045244 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.8179. Min Act: -0.0000

Data Index: 901967 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.9529. Min Act: -0.0000

Data Index: 993945 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.0757. Min Act: -0.0000

Data Index: 911649 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.8089. Min Act: -0.0000

Data Index: 252596 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 4.1607. Min Range: -4.1607

Max Act: 3.0610. Min Act: -0.0000

Data Index: 535134 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.8915. Min Act: -0.0000

Data Index: 1266474 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.8744. Min Act: -0.0000

Data Index: 276687 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.8077. Min Act: -0.0000

Data Index: 1028259 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.7746. Min Act: -0.0000

Data Index: 860484 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.6063. Min Act: -0.0000

Data Index: 176023 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.7221. Min Act: -0.0000

Data Index: 807603 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 4.1607. Min Range: -4.1607

Max Act: 2.7266. Min Act: -0.0000

Data Index: 149310 (C4 (Web Text))

Max Activating Token Index: 52