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

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

Neuron 5029 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.1018. Min Act: -0.0000

Data Index: 1590984 (Python Code)

Max Activating Token Index: 793

Text #1

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0444. Min Act: -0.0000

Data Index: 1532950 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1619572 (Python Code)

Max Activating Token Index: 356

Text #3

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0590. Min Act: -0.0000

Data Index: 598158 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9697. Min Act: -0.0000

Data Index: 496718 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1029851 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0080. Min Act: -0.0000

Data Index: 144171 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0752. Min Act: -0.0000

Data Index: 1517848 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1438714 (Python Code)

Max Activating Token Index: 274

Text #9

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.0062. Min Act: -0.0000

Data Index: 398476 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.1030. Min Range: -1.1030

Max Act: 1.1030. Min Act: -0.0000

Data Index: 947359 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1639283 (Python Code)

Max Activating Token Index: 872

Text #12

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8688. Min Act: -0.0000

Data Index: 666446 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.9351. Min Act: -0.0000

Data Index: 260562 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1506430 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8380. Min Act: -0.0000

Data Index: 524108 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1565586 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1585370 (Python Code)

Max Activating Token Index: 869

Text #18

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.8626. Min Act: -0.0000

Data Index: 382606 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.1030. Min Range: -1.1030

Max Act: 0.7917. Min Act: -0.0000

Data Index: 221346 (C4 (Web Text))

Max Activating Token Index: 265