Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4310 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2562. Min Range: -1.2562

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1602693 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 1.2562. Min Range: -1.2562

Max Act: 1.0774. Min Act: -0.0000

Data Index: 1633555 (Python Code)

Max Activating Token Index: 1017

Text #2

Max Range: 1.2562. Min Range: -1.2562

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1438575 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1573593 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.9122. Min Act: -0.0000

Data Index: 1457274 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1432490 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1495213 (Python Code)

Max Activating Token Index: 685

Text #7

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1631476 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1401347 (Python Code)

Max Activating Token Index: 128

Text #9

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1487555 (Python Code)

Max Activating Token Index: 979

Text #10

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1471470 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1462291 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1386610 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1626100 (Python Code)

Max Activating Token Index: 441

Text #14

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1577101 (Python Code)

Max Activating Token Index: 787

Text #15

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1651632 (Python Code)

Max Activating Token Index: 547

Text #16

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1456940 (Python Code)

Max Activating Token Index: 710

Text #17

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8592. Min Act: -0.0000

Data Index: 1438054 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1538654 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 1.2562. Min Range: -1.2562

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1443819 (Python Code)

Max Activating Token Index: 589