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

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

Neuron 2469 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: 2.2544. Min Range: -2.2544

Max Act: 2.2544. Min Act: -0.0000

Data Index: 837978 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 2.2544. Min Range: -2.2544

Max Act: 2.0449. Min Act: -0.0000

Data Index: 1149070 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.6228. Min Act: -0.0000

Data Index: 568162 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.5218. Min Act: -0.0000

Data Index: 75463 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.5424. Min Act: -0.0000

Data Index: 1557659 (Python Code)

Max Activating Token Index: 944

Text #5

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.4929. Min Act: -0.0000

Data Index: 1257803 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1021792 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.3308. Min Act: -0.0000

Data Index: 655555 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.3480. Min Act: -0.0001

Data Index: 851260 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.3162. Min Act: -0.0000

Data Index: 1397517 (Python Code)

Max Activating Token Index: 829

Text #10

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.2314. Min Act: -0.0001

Data Index: 1528694 (Python Code)

Max Activating Token Index: 415

Text #11

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.2372. Min Act: -0.0000

Data Index: 676131 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.1702. Min Act: -0.0000

Data Index: 737063 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.2247. Min Act: -0.0001

Data Index: 974161 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.1374. Min Act: -0.0000

Data Index: 291484 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1624151 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1409980 (Python Code)

Max Activating Token Index: 995

Text #17

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1575020 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.0824. Min Act: -0.0000

Data Index: 136844 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 2.2544. Min Range: -2.2544

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1312978 (C4 (Web Text))

Max Activating Token Index: 746