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

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

Neuron 3585 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: 0.5103. Min Range: -0.5103

Max Act: 0.5103. Min Act: -0.0000

Data Index: 859795 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4730. Min Act: -0.0000

Data Index: 640720 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4644. Min Act: -0.0001

Data Index: 541167 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4869. Min Act: -0.0001

Data Index: 192398 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4648. Min Act: -0.0001

Data Index: 176833 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1260948 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1358777 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1198533 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4448. Min Act: -0.0000

Data Index: 721129 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4561. Min Act: -0.0000

Data Index: 231060 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4356. Min Act: -0.0000

Data Index: 874222 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4516. Min Act: -0.0000

Data Index: 94609 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4203. Min Act: -0.0000

Data Index: 398632 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4219. Min Act: -0.0001

Data Index: 488604 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4217. Min Act: -0.0000

Data Index: 490396 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4231. Min Act: -0.0000

Data Index: 100183 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1053694 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1288514 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1325785 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.5103. Min Range: -0.5103

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1264766 (C4 (Web Text))

Max Activating Token Index: 412