Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.8383. Min Act: -0.0001

Data Index: 444444 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.7660. Min Act: -0.0001

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.7800. Min Act: -0.0001

Data Index: 739401 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.7710. Min Act: -0.0001

Data Index: 124503 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.8006. Min Act: -0.0001

Data Index: 271451 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.6246. Min Act: -0.0001

Data Index: 1202074 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.6564. Min Act: -0.0001

Data Index: 679466 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.7912. Min Act: -0.0001

Data Index: 813953 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.5997. Min Act: -0.0001

Data Index: 1001203 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.5417. Min Act: -0.0001

Data Index: 620559 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.6180. Min Act: -0.0001

Data Index: 1255926 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4342. Min Act: -0.0001

Data Index: 122985 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.6106. Min Act: -0.0001

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4669. Min Act: -0.0001

Data Index: 1176276 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.5947. Min Act: -0.0001

Data Index: 1337550 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4868. Min Act: -0.0001

Data Index: 164590 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4780. Min Act: -0.0001

Data Index: 1184785 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4760. Min Act: -0.0001

Data Index: 500316 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.3849. Min Act: -0.0001

Data Index: 307405 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 1.8383. Min Range: -1.8383

Max Act: 1.4560. Min Act: -0.0001

Data Index: 201603 (C4 (Web Text))

Max Activating Token Index: 259