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

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

Neuron 751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4409. Min Act: -0.0002

Data Index: 57303 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4478. Min Act: -0.0002

Data Index: 893471 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4040. Min Act: -0.0001

Data Index: 927351 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4023. Min Act: -0.0002

Data Index: 574408 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4023. Min Act: -0.0001

Data Index: 1202277 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3861. Min Act: -0.0002

Data Index: 631605 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3890. Min Act: -0.0001

Data Index: 740012 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.4182. Min Act: -0.0002

Data Index: 702447 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3959. Min Act: -0.0002

Data Index: 1351232 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3658. Min Act: -0.0001

Data Index: 721327 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3650. Min Act: -0.0002

Data Index: 639482 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3953. Min Act: -0.0001

Data Index: 449055 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1230429 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3829. Min Act: -0.0002

Data Index: 833454 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3701. Min Act: -0.0002

Data Index: 1275246 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3982. Min Act: -0.0002

Data Index: 729775 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3649. Min Act: -0.0002

Data Index: 175171 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3588. Min Act: -0.0001

Data Index: 591606 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3562. Min Act: -0.0002

Data Index: 657433 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 0.4478. Min Range: -0.4478

Max Act: 0.3672. Min Act: -0.0002

Data Index: 621950 (C4 (Web Text))

Max Activating Token Index: 7