Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2962 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1389373 (Python Code)

Max Activating Token Index: 445

Text #1

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1468746 (Python Code)

Max Activating Token Index: 564

Text #2

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1458217 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1625035 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1398927 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4786. Min Act: -0.0001

Data Index: 1639479 (Python Code)

Max Activating Token Index: 946

Text #6

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1407920 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4596. Min Act: -0.0001

Data Index: 1423897 (Python Code)

Max Activating Token Index: 890

Text #8

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4730. Min Act: -0.0001

Data Index: 1496537 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1590133 (Python Code)

Max Activating Token Index: 173

Text #10

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4179. Min Act: -0.0001

Data Index: 1365505 (Python Code)

Max Activating Token Index: 830

Text #11

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1449991 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3950. Min Act: -0.0000

Data Index: 76330 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3785. Min Act: -0.0000

Data Index: 229821 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3564. Min Act: 0.0000

Data Index: 173405 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3536. Min Act: -0.0000

Data Index: 341405 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3611. Min Act: 0.0001

Data Index: 293547 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3562. Min Act: -0.0000

Data Index: 519009 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3558. Min Act: 0.0000

Data Index: 995511 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.5505. Min Range: -0.5505

Max Act: 0.3385. Min Act: -0.0000

Data Index: 835519 (C4 (Web Text))

Max Activating Token Index: 570