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

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

Neuron 871 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4528. Min Act: -0.0000

Data Index: 417232 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4136. Min Act: -0.0000

Data Index: 528344 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4767. Min Act: -0.0000

Data Index: 76048 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4847. Min Act: -0.0000

Data Index: 386461 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3707. Min Act: -0.0000

Data Index: 139458 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4034. Min Act: -0.0000

Data Index: 242774 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4263. Min Act: -0.0000

Data Index: 316894 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4220. Min Act: -0.0000

Data Index: 796140 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3861. Min Act: -0.0000

Data Index: 349691 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3428. Min Act: -0.0000

Data Index: 627731 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3317. Min Act: -0.0000

Data Index: 40540 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3552. Min Act: -0.0000

Data Index: 373096 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1166249 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1344941 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3617. Min Act: -0.0000

Data Index: 559428 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3505. Min Act: -0.0000

Data Index: 435397 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3484. Min Act: -0.0000

Data Index: 265968 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4221. Min Act: -0.0000

Data Index: 153999 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3697. Min Act: -0.0000

Data Index: 387712 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1540887 (Python Code)

Max Activating Token Index: 961