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

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

Neuron 1951 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.8630. Min Act: -0.0001

Data Index: 1447133 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.8255. Min Act: -0.0001

Data Index: 1467688 (Python Code)

Max Activating Token Index: 345

Text #2

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7351. Min Act: -0.0001

Data Index: 1515446 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7217. Min Act: -0.0001

Data Index: 1550811 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6982. Min Act: -0.0001

Data Index: 1543366 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6974. Min Act: -0.0001

Data Index: 1399676 (Python Code)

Max Activating Token Index: 116

Text #6

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7146. Min Act: -0.0001

Data Index: 1603121 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6540. Min Act: -0.0001

Data Index: 1430553 (Python Code)

Max Activating Token Index: 224

Text #8

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7036. Min Act: -0.0001

Data Index: 1436354 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6908. Min Act: -0.0001

Data Index: 1635095 (Python Code)

Max Activating Token Index: 358

Text #10

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6646. Min Act: -0.0001

Data Index: 1649104 (Python Code)

Max Activating Token Index: 475

Text #11

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6450. Min Act: -0.0001

Data Index: 1584214 (Python Code)

Max Activating Token Index: 1012

Text #12

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6807. Min Act: -0.0001

Data Index: 1446468 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6531. Min Act: -0.0001

Data Index: 1567252 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1564113 (Python Code)

Max Activating Token Index: 311

Text #15

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6139. Min Act: -0.0001

Data Index: 1472697 (Python Code)

Max Activating Token Index: 529

Text #16

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1529390 (Python Code)

Max Activating Token Index: 314

Text #17

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6302. Min Act: -0.0001

Data Index: 1412141 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6293. Min Act: -0.0001

Data Index: 1427797 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.5814. Min Act: -0.0001

Data Index: 1373964 (Python Code)

Max Activating Token Index: 584