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

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

Neuron 4288 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.9230. Min Act: -0.0002

Data Index: 533875 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8717. Min Act: -0.0002

Data Index: 1224566 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8687. Min Act: -0.0002

Data Index: 683127 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8548. Min Act: -0.0002

Data Index: 251361 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8486. Min Act: -0.0002

Data Index: 744768 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8499. Min Act: -0.0002

Data Index: 304300 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8372. Min Act: -0.0002

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8392. Min Act: -0.0002

Data Index: 472354 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8453. Min Act: -0.0002

Data Index: 941479 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8305. Min Act: -0.0002

Data Index: 582302 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8211. Min Act: -0.0002

Data Index: 666332 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8076. Min Act: -0.0002

Data Index: 734924 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.8012. Min Act: -0.0002

Data Index: 742824 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7970. Min Act: -0.0002

Data Index: 226453 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7874. Min Act: -0.0002

Data Index: 559455 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7894. Min Act: -0.0002

Data Index: 1011550 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7771. Min Act: -0.0002

Data Index: 735535 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7748. Min Act: -0.0002

Data Index: 976184 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7863. Min Act: -0.0002

Data Index: 35401 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.9230. Min Range: -0.9230

Max Act: 0.7796. Min Act: -0.0002

Data Index: 24469 (C4 (Web Text))

Max Activating Token Index: 758