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

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

Neuron 5079 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: 0.4759. Min Range: -0.4759

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1361321 (Python Code)

Max Activating Token Index: 900

Text #1

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1638809 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1508163 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4239. Min Act: -0.0000

Data Index: 1430052 (Python Code)

Max Activating Token Index: 122

Text #4

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1438457 (Python Code)

Max Activating Token Index: 510

Text #5

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1518464 (Python Code)

Max Activating Token Index: 336

Text #6

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1509613 (Python Code)

Max Activating Token Index: 235

Text #7

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1567518 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3844. Min Act: -0.0000

Data Index: 1601058 (Python Code)

Max Activating Token Index: 676

Text #9

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1523965 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1457315 (Python Code)

Max Activating Token Index: 914

Text #11

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1608921 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1633480 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1593485 (Python Code)

Max Activating Token Index: 379

Text #14

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1438399 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1387325 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1559048 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3111. Min Act: -0.0000

Data Index: 1361449 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3661. Min Act: -0.0000

Data Index: 1409918 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3559. Min Act: -0.0001

Data Index: 1574307 (Python Code)

Max Activating Token Index: 563