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

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

Neuron 3820 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.5313. Min Act: -0.0001

Data Index: 173907 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4437. Min Act: -0.0000

Data Index: 182994 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4410. Min Act: -0.0000

Data Index: 361799 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1111183 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4212. Min Act: -0.0001

Data Index: 178877 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3984. Min Act: -0.0000

Data Index: 767590 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4086. Min Act: -0.0001

Data Index: 568336 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4067. Min Act: -0.0001

Data Index: 817373 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3883. Min Act: -0.0001

Data Index: 211823 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1281785 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3786. Min Act: -0.0001

Data Index: 867623 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3631. Min Act: -0.0001

Data Index: 204479 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3623. Min Act: -0.0001

Data Index: 242241 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3675. Min Act: -0.0000

Data Index: 895470 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3632. Min Act: -0.0000

Data Index: 171559 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3715. Min Act: -0.0001

Data Index: 285284 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3502. Min Act: -0.0001

Data Index: 628952 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1357119 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3632. Min Act: -0.0001

Data Index: 477815 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3561. Min Act: -0.0001

Data Index: 621478 (C4 (Web Text))

Max Activating Token Index: 252