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

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

Neuron 1970 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: 0.5001. Min Range: -0.5001

Max Act: 0.5001. Min Act: -0.0001

Data Index: 57448 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.4714. Min Act: -0.0000

Data Index: 502860 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1265231 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.4029. Min Act: -0.0001

Data Index: 68268 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.3728. Min Act: -0.0001

Data Index: 1039011 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.3849. Min Act: -0.0001

Data Index: 64701 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.3417. Min Act: -0.0001

Data Index: 1339381 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.3317. Min Act: -0.0001

Data Index: 460619 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.3476. Min Act: -0.0001

Data Index: 502206 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.4127. Min Act: -0.0000

Data Index: 683985 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2722. Min Act: -0.0001

Data Index: 1069418 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2685. Min Act: -0.0001

Data Index: 478894 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.1934. Min Act: -0.0001

Data Index: 586128 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2714. Min Act: -0.0001

Data Index: 264325 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2813. Min Act: -0.0001

Data Index: 1605194 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2821. Min Act: -0.0001

Data Index: 390549 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.3006. Min Act: -0.0001

Data Index: 251728 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1597742 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2634. Min Act: -0.0000

Data Index: 1099649 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.5001. Min Range: -0.5001

Max Act: 0.2543. Min Act: -0.0001

Data Index: 402438 (C4 (Web Text))

Max Activating Token Index: 970