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

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

Neuron 3404 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.8465. Min Act: -0.0001

Data Index: 439702 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.6189. Min Act: -0.0001

Data Index: 1054001 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.5655. Min Act: -0.0001

Data Index: 1205320 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1005548 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.5080. Min Act: -0.0001

Data Index: 956479 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.5419. Min Act: -0.0001

Data Index: 914601 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4927. Min Act: -0.0001

Data Index: 470950 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4892. Min Act: -0.0001

Data Index: 1028713 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4903. Min Act: -0.0000

Data Index: 694962 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4919. Min Act: -0.0000

Data Index: 407379 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4760. Min Act: -0.0001

Data Index: 260446 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.5045. Min Act: -0.0000

Data Index: 451341 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1055648 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1011443 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4714. Min Act: -0.0001

Data Index: 635924 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4503. Min Act: -0.0000

Data Index: 507882 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4803. Min Act: -0.0000

Data Index: 251414 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1036912 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4675. Min Act: -0.0001

Data Index: 1450283 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 0.8465. Min Range: -0.8465

Max Act: 0.4675. Min Act: -0.0001

Data Index: 582159 (C4 (Web Text))

Max Activating Token Index: 440