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

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

Neuron 3566 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.9800. Min Act: -0.0001

Data Index: 513968 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.9191. Min Act: -0.0001

Data Index: 326222 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8908. Min Act: -0.0001

Data Index: 404343 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8347. Min Act: -0.0001

Data Index: 1324732 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7792. Min Act: -0.0001

Data Index: 268690 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8102. Min Act: -0.0001

Data Index: 1088792 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7381. Min Act: -0.0001

Data Index: 217654 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7486. Min Act: -0.0001

Data Index: 1315017 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7393. Min Act: -0.0001

Data Index: 1094906 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7427. Min Act: -0.0001

Data Index: 303186 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7555. Min Act: -0.0001

Data Index: 1161029 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8092. Min Act: -0.0001

Data Index: 1356106 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7703. Min Act: -0.0001

Data Index: 1295165 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.6936. Min Act: -0.0001

Data Index: 681177 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7105. Min Act: -0.0001

Data Index: 930525 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7545. Min Act: -0.0001

Data Index: 523966 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.6779. Min Act: -0.0001

Data Index: 244144 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7339. Min Act: -0.0001

Data Index: 1212190 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.6599. Min Act: -0.0001

Data Index: 767356 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.6725. Min Act: -0.0001

Data Index: 548615 (C4 (Web Text))

Max Activating Token Index: 54