Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1339 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: -0.0001

Data Index: 26395 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.2255. Min Act: -0.0001

Data Index: 468927 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0298. Min Act: -0.0001

Data Index: 496079 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0364. Min Act: -0.0001

Data Index: 347105 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9451. Min Act: -0.0001

Data Index: 459822 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9528. Min Act: -0.0001

Data Index: 1213722 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9428. Min Act: -0.0001

Data Index: 302132 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9163. Min Act: -0.0001

Data Index: 878771 (C4 (Web Text))

Max Activating Token Index: 919

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9736. Min Act: -0.0001

Data Index: 761104 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9452. Min Act: -0.0001

Data Index: 453757 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9492. Min Act: -0.0001

Data Index: 1033678 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9830. Min Act: -0.0001

Data Index: 331654 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8687. Min Act: -0.0001

Data Index: 651128 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8838. Min Act: -0.0001

Data Index: 985164 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8323. Min Act: -0.0001

Data Index: 1065065 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8852. Min Act: -0.0001

Data Index: 1173045 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8530. Min Act: -0.0001

Data Index: 1062588 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1057761 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8863. Min Act: -0.0001

Data Index: 391691 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7715. Min Act: -0.0001

Data Index: 884760 (C4 (Web Text))

Max Activating Token Index: 600