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

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

Neuron 5670 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.8314. Min Act: -0.0000

Data Index: 304477 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.7568. Min Act: -0.0000

Data Index: 991280 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.8830. Min Act: -0.0000

Data Index: 933363 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.9558. Min Act: -0.0000

Data Index: 450555 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.9564. Min Act: -0.0001

Data Index: 336897 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.6878. Min Act: -0.0000

Data Index: 151697 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.6703. Min Act: -0.0000

Data Index: 679386 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5517. Min Act: -0.0000

Data Index: 1347985 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.7340. Min Act: -0.0000

Data Index: 313941 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.6377. Min Act: -0.0000

Data Index: 467581 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.3330. Min Act: -0.0001

Data Index: 184867 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5718. Min Act: -0.0000

Data Index: 1221622 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5551. Min Act: -0.0001

Data Index: 1043472 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.3839. Min Act: -0.0000

Data Index: 763508 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5353. Min Act: -0.0001

Data Index: 810814 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4686. Min Act: -0.0000

Data Index: 938160 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5318. Min Act: -0.0000

Data Index: 81497 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.5213. Min Act: -0.0000

Data Index: 791286 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1099422 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 1.9564. Min Range: -1.9564

Max Act: 1.4703. Min Act: -0.0000

Data Index: 1102325 (C4 (Web Text))

Max Activating Token Index: 461