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

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

Neuron 2730 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: 0.9627. Min Range: -0.9627

Max Act: 0.9627. Min Act: -0.0000

Data Index: 1292337 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8808. Min Act: -0.0000

Data Index: 1322107 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8557. Min Act: -0.0000

Data Index: 696703 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1438856 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7720. Min Act: -0.0000

Data Index: 1379680 (Python Code)

Max Activating Token Index: 370

Text #5

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1614851 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1436874 (Python Code)

Max Activating Token Index: 898

Text #7

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6527. Min Act: -0.0000

Data Index: 9129 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1529835 (Python Code)

Max Activating Token Index: 476

Text #9

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1548520 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1574503 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1548342 (Python Code)

Max Activating Token Index: 570

Text #12

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1508136 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1396222 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1420691 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1590502 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1466196 (Python Code)

Max Activating Token Index: 802

Text #17

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6599. Min Act: -0.0000

Data Index: 294454 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1444428 (Python Code)

Max Activating Token Index: 1005

Text #19

Max Range: 0.9627. Min Range: -0.9627

Max Act: 0.6909. Min Act: -0.0000

Data Index: 1623596 (Python Code)

Max Activating Token Index: 875