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

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

Neuron 3207 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1239613 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1281048 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1516696 (Python Code)

Max Activating Token Index: 580

Text #3

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1082850 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1503489 (Python Code)

Max Activating Token Index: 884

Text #5

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1534798 (Python Code)

Max Activating Token Index: 877

Text #6

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7830. Min Act: -0.0000

Data Index: 387765 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.8112. Min Act: -0.0000

Data Index: 460415 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7338. Min Act: -0.0000

Data Index: 351159 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7582. Min Act: -0.0000

Data Index: 404697 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7506. Min Act: -0.0000

Data Index: 24548 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1526390 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7289. Min Act: -0.0000

Data Index: 626692 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.6801. Min Act: -0.0000

Data Index: 959645 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.6828. Min Act: -0.0000

Data Index: 425762 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.7138. Min Act: -0.0000

Data Index: 820118 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.6757. Min Act: -0.0000

Data Index: 857260 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.6935. Min Act: -0.0000

Data Index: 145906 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.6921. Min Act: -0.0000

Data Index: 75569 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.9077. Min Range: -0.9077

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1467162 (Python Code)

Max Activating Token Index: 101