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

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

Neuron 2673 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: 4.8966. Min Range: -4.8966

Max Act: 4.8966. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.6674. Min Act: -0.0000

Data Index: 165600 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.4544. Min Act: -0.0000

Data Index: 1057009 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.7667. Min Act: -0.0000

Data Index: 676719 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.5318. Min Act: -0.0000

Data Index: 1177874 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.2666. Min Act: -0.0000

Data Index: 364664 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.2504. Min Act: -0.0000

Data Index: 1070395 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.2203. Min Act: -0.0000

Data Index: 223582 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.1824. Min Act: -0.0000

Data Index: 1240358 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.3566. Min Act: -0.0000

Data Index: 661064 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.1416. Min Act: -0.0000

Data Index: 79438 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.0794. Min Act: -0.0000

Data Index: 426273 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 4.8966. Min Range: -4.8966

Max Act: 4.1050. Min Act: -0.0000

Data Index: 321083 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 4.8966. Min Range: -4.8966

Max Act: 3.9287. Min Act: -0.0000

Data Index: 348597 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 4.8966. Min Range: -4.8966

Max Act: 3.9260. Min Act: -0.0000

Data Index: 375627 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 4.8966. Min Range: -4.8966

Max Act: 3.9644. Min Act: -0.0000

Data Index: 1014762 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 4.8966. Min Range: -4.8966

Max Act: 3.8456. Min Act: -0.0000

Data Index: 408700 (C4 (Web Text))

Max Activating Token Index: 377

Text #17

Max Range: 4.8966. Min Range: -4.8966

Max Act: 3.4534. Min Act: -0.0000

Data Index: 1243427 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 4.8966. Min Range: -4.8966

Max Act: 3.5599. Min Act: -0.0000

Data Index: 84602 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 4.8966. Min Range: -4.8966

Max Act: 3.3379. Min Act: -0.0000

Data Index: 1088532 (C4 (Web Text))

Max Activating Token Index: 359