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

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

Neuron 715 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1603909 (Python Code)

Max Activating Token Index: 424

Text #1

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5259. Min Act: -0.0000

Data Index: 928354 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4617. Min Act: -0.0000

Data Index: 247474 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4405. Min Act: 0.0000

Data Index: 1212593 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1126004 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4289. Min Act: -0.0000

Data Index: 539901 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4130. Min Act: 0.0000

Data Index: 62114 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.4003. Min Act: -0.0000

Data Index: 438606 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3929. Min Act: 0.0000

Data Index: 1078346 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1383494 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1144576 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3654. Min Act: -0.0000

Data Index: 937552 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3408. Min Act: -0.0000

Data Index: 859011 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3836. Min Act: -0.0000

Data Index: 198252 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3657. Min Act: -0.0000

Data Index: 891967 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3447. Min Act: -0.0000

Data Index: 886663 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3647. Min Act: -0.0000

Data Index: 38284 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3654. Min Act: -0.0000

Data Index: 963250 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1120012 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.3701. Min Act: -0.0000

Data Index: 409595 (C4 (Web Text))

Max Activating Token Index: 22