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

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

Neuron 488 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: 1.3801. Min Range: -1.3801

Max Act: 1.3241. Min Act: -0.0000

Data Index: 104976 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.3801. Min Act: -0.0000

Data Index: 190482 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.3097. Min Act: -0.0000

Data Index: 686501 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2806. Min Act: -0.0000

Data Index: 648455 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2438. Min Act: -0.0000

Data Index: 414364 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2375. Min Act: -0.0000

Data Index: 36048 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.2048. Min Act: -0.0000

Data Index: 697413 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0449. Min Act: -0.0000

Data Index: 288732 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.1001. Min Act: -0.0000

Data Index: 42323 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0998. Min Act: -0.0000

Data Index: 805716 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0033. Min Act: -0.0000

Data Index: 485691 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0392. Min Act: -0.0000

Data Index: 469205 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0156. Min Act: -0.0000

Data Index: 113807 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0695. Min Act: -0.0000

Data Index: 984201 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1048981 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.3801. Min Range: -1.3801

Max Act: 1.0137. Min Act: -0.0000

Data Index: 305226 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 1.3801. Min Range: -1.3801

Max Act: 0.9786. Min Act: -0.0000

Data Index: 357415 (C4 (Web Text))

Max Activating Token Index: 588

Text #17

Max Range: 1.3801. Min Range: -1.3801

Max Act: 0.8482. Min Act: -0.0000

Data Index: 783421 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 1.3801. Min Range: -1.3801

Max Act: 0.9067. Min Act: -0.0000

Data Index: 10324 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 1.3801. Min Range: -1.3801

Max Act: 0.9324. Min Act: -0.0000

Data Index: 869024 (C4 (Web Text))

Max Activating Token Index: 730