Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4304 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.6156. Min Act: -0.0000

Data Index: 405947 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5702. Min Act: -0.0000

Data Index: 899676 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5338. Min Act: -0.0000

Data Index: 804366 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5198. Min Act: -0.0000

Data Index: 900993 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.5186. Min Act: -0.0000

Data Index: 564682 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4772. Min Act: -0.0000

Data Index: 343504 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1201209 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4577. Min Act: -0.0000

Data Index: 809861 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4855. Min Act: -0.0000

Data Index: 816901 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4352. Min Act: -0.0000

Data Index: 174150 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4458. Min Act: -0.0000

Data Index: 88259 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4232. Min Act: -0.0000

Data Index: 960352 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4080. Min Act: -0.0000

Data Index: 169272 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.3948. Min Act: -0.0000

Data Index: 730482 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4644. Min Act: -0.0000

Data Index: 218143 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4308. Min Act: -0.0000

Data Index: 16013 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4160. Min Act: -0.0000

Data Index: 571752 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.4136. Min Act: -0.0000

Data Index: 546594 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.3851. Min Act: -0.0000

Data Index: 234243 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.6156. Min Range: -0.6156

Max Act: 0.3904. Min Act: -0.0000

Data Index: 731471 (C4 (Web Text))

Max Activating Token Index: 924