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

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

Neuron 4262 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: 0.6531. Min Range: -0.6531

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1425276 (Python Code)

Max Activating Token Index: 807

Text #1

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.5807. Min Act: -0.0000

Data Index: 1540751 (Python Code)

Max Activating Token Index: 706

Text #2

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.5781. Min Act: -0.0000

Data Index: 1396301 (Python Code)

Max Activating Token Index: 821

Text #3

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1532150 (Python Code)

Max Activating Token Index: 207

Text #4

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1567398 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1479001 (Python Code)

Max Activating Token Index: 804

Text #6

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1471991 (Python Code)

Max Activating Token Index: 486

Text #7

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4646. Min Act: -0.0000

Data Index: 1590790 (Python Code)

Max Activating Token Index: 105

Text #8

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4389. Min Act: -0.0000

Data Index: 544113 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1614396 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1374546 (Python Code)

Max Activating Token Index: 788

Text #11

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4436. Min Act: -0.0000

Data Index: 380494 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1521403 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1499469 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1374603 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.3788. Min Act: -0.0000

Data Index: 16425 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1558825 (Python Code)

Max Activating Token Index: 587

Text #17

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1649856 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4055. Min Act: -0.0000

Data Index: 1610862 (Python Code)

Max Activating Token Index: 317

Text #19

Max Range: 0.6531. Min Range: -0.6531

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1522019 (Python Code)

Max Activating Token Index: 120