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

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

Neuron 3431 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: 0.1275. Min Range: -0.1275

Max Act: 0.1265. Min Act: -0.0000

Data Index: 990320 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1275. Min Act: -0.0000

Data Index: 741442 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1272147 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1087. Min Act: -0.0000

Data Index: 526611 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1004. Min Act: -0.0000

Data Index: 766380 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0985. Min Act: -0.0000

Data Index: 755337 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1094243 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0992. Min Act: -0.0000

Data Index: 717795 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0966. Min Act: -0.0000

Data Index: 160087 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0863. Min Act: -0.0000

Data Index: 329705 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0910. Min Act: -0.0000

Data Index: 480072 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1033136 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0911. Min Act: -0.0000

Data Index: 415644 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0906. Min Act: -0.0000

Data Index: 249410 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0869. Min Act: -0.0000

Data Index: 511054 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0892. Min Act: -0.0000

Data Index: 144415 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0845. Min Act: -0.0000

Data Index: 586349 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0848. Min Act: -0.0000

Data Index: 411281 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0815. Min Act: -0.0000

Data Index: 45152 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0893. Min Act: -0.0000

Data Index: 920834 (C4 (Web Text))

Max Activating Token Index: 678