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

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

Neuron 3731 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.7476. Min Act: -0.0003

Data Index: 1154320 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5378. Min Act: -0.0002

Data Index: 280759 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5438. Min Act: -0.0003

Data Index: 409972 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5154. Min Act: -0.0003

Data Index: 518669 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5012. Min Act: -0.0003

Data Index: 1258980 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4840. Min Act: -0.0003

Data Index: 1110528 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4891. Min Act: -0.0003

Data Index: 609177 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5014. Min Act: -0.0002

Data Index: 769919 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.5005. Min Act: -0.0003

Data Index: 751111 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4727. Min Act: -0.0002

Data Index: 1305588 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4863. Min Act: -0.0003

Data Index: 367166 (C4 (Web Text))

Max Activating Token Index: 465

Text #11

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4623. Min Act: -0.0003

Data Index: 337338 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4530. Min Act: -0.0003

Data Index: 884581 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4453. Min Act: -0.0003

Data Index: 349180 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4434. Min Act: -0.0002

Data Index: 1386036 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4391. Min Act: -0.0003

Data Index: 1374914 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4385. Min Act: -0.0002

Data Index: 914954 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4356. Min Act: -0.0002

Data Index: 986749 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4360. Min Act: -0.0002

Data Index: 1516168 (Python Code)

Max Activating Token Index: 646

Text #19

Max Range: 0.7476. Min Range: -0.7476

Max Act: 0.4353. Min Act: -0.0003

Data Index: 1362642 (Python Code)

Max Activating Token Index: 451