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

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

Neuron 4510 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1440418 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3643. Min Act: -0.0000

Data Index: 1538522 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3467. Min Act: -0.0000

Data Index: 1619299 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.3462. Min Act: -0.0000

Data Index: 1543325 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.2663. Min Act: -0.0000

Data Index: 1484992 (Python Code)

Max Activating Token Index: 1006

Text #5

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.2018. Min Act: -0.0000

Data Index: 1440691 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1536242 (Python Code)

Max Activating Token Index: 974

Text #7

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1414382 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1304906 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.0521. Min Act: -0.0000

Data Index: 917587 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 1.7821. Min Range: -1.7821

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1379376 (Python Code)

Max Activating Token Index: 752

Text #11

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.8524. Min Act: -0.0000

Data Index: 385666 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1501767 (Python Code)

Max Activating Token Index: 113

Text #13

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1639708 (Python Code)

Max Activating Token Index: 287

Text #14

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.9450. Min Act: -0.0000

Data Index: 473681 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1381035 (Python Code)

Max Activating Token Index: 800

Text #16

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.8999. Min Act: -0.0000

Data Index: 892333 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.9843. Min Act: -0.0000

Data Index: 788327 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1478153 (Python Code)

Max Activating Token Index: 374

Text #19

Max Range: 1.7821. Min Range: -1.7821

Max Act: 0.9580. Min Act: -0.0000

Data Index: 46892 (C4 (Web Text))

Max Activating Token Index: 523