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

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

Neuron 5017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.9809. Min Act: -0.0000

Data Index: 960103 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.9632. Min Act: -0.0000

Data Index: 811220 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8962. Min Act: -0.0000

Data Index: 221597 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.9477. Min Act: -0.0001

Data Index: 277736 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.9499. Min Act: -0.0000

Data Index: 973771 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8337. Min Act: -0.0001

Data Index: 558003 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1463817 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.9067. Min Act: -0.0000

Data Index: 47299 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1224314 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8983. Min Act: -0.0001

Data Index: 110432 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8666. Min Act: -0.0000

Data Index: 1204728 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1021697 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8497. Min Act: -0.0001

Data Index: 719271 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8717. Min Act: -0.0000

Data Index: 251770 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8431. Min Act: -0.0000

Data Index: 1315996 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1251245 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1296634 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1039101 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1243822 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.9809. Min Range: -0.9809

Max Act: 0.8209. Min Act: -0.0001

Data Index: 1335340 (C4 (Web Text))

Max Activating Token Index: 493