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

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

Neuron 4703 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: 1.4099. Min Range: -1.4099

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1249483 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.2073. Min Act: -0.0000

Data Index: 85622 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.2025. Min Act: -0.0000

Data Index: 796611 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1318359 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.1357. Min Act: -0.0000

Data Index: 446075 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.1268. Min Act: -0.0000

Data Index: 748088 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0581. Min Act: -0.0000

Data Index: 326658 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.1282. Min Act: -0.0000

Data Index: 552564 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.1857. Min Act: -0.0000

Data Index: 198930 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.1608. Min Act: -0.0000

Data Index: 402592 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0844. Min Act: -0.0000

Data Index: 348708 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1141862 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0652. Min Act: -0.0000

Data Index: 656233 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1334055 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1343530 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0121. Min Act: -0.0000

Data Index: 881617 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1165864 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.4099. Min Range: -1.4099

Max Act: 0.9081. Min Act: -0.0000

Data Index: 972851 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 1.4099. Min Range: -1.4099

Max Act: 0.9683. Min Act: -0.0000

Data Index: 569809 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.4099. Min Range: -1.4099

Max Act: 1.0312. Min Act: -0.0000

Data Index: 927530 (C4 (Web Text))

Max Activating Token Index: 999