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

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

Neuron 3459 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.5631. Min Act: -0.0001

Data Index: 408193 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.5828. Min Act: -0.0000

Data Index: 630078 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.5231. Min Act: -0.0000

Data Index: 820331 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1060744 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4499. Min Act: -0.0001

Data Index: 781493 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4241. Min Act: -0.0001

Data Index: 201307 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4402. Min Act: -0.0000

Data Index: 813829 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4167. Min Act: -0.0000

Data Index: 678054 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4427. Min Act: -0.0001

Data Index: 1166974 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1306965 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4026. Min Act: -0.0000

Data Index: 326723 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4012. Min Act: -0.0001

Data Index: 604274 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.4252. Min Act: -0.0000

Data Index: 729385 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.3963. Min Act: -0.0001

Data Index: 246702 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.3965. Min Act: -0.0000

Data Index: 239935 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.3667. Min Act: -0.0000

Data Index: 1176601 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.3878. Min Act: -0.0001

Data Index: 459647 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1130263 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.3817. Min Act: -0.0001

Data Index: 6571 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.5828. Min Range: -0.5828

Max Act: 0.3675. Min Act: -0.0001

Data Index: 882559 (C4 (Web Text))

Max Activating Token Index: 750