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

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

Neuron 1925 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.5049. Min Act: -0.0001

Data Index: 693662 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4131. Min Act: -0.0001

Data Index: 501311 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3965. Min Act: -0.0001

Data Index: 994313 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3796. Min Act: -0.0001

Data Index: 923546 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3233. Min Act: -0.0001

Data Index: 1131323 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2829. Min Act: -0.0001

Data Index: 1135527 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2474. Min Act: -0.0001

Data Index: 630797 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.1680. Min Act: -0.0001

Data Index: 327606 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9736. Min Act: -0.0001

Data Index: 51754 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0290. Min Act: -0.0001

Data Index: 1571289 (Python Code)

Max Activating Token Index: 771

Text #10

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9647. Min Act: -0.0001

Data Index: 522712 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9504. Min Act: -0.0001

Data Index: 942810 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9136. Min Act: -0.0001

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9477. Min Act: -0.0001

Data Index: 891877 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9715. Min Act: -0.0001

Data Index: 1446567 (Python Code)

Max Activating Token Index: 376

Text #15

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9291. Min Act: -0.0001

Data Index: 1024069 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9142. Min Act: -0.0001

Data Index: 483339 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.8350. Min Act: -0.0001

Data Index: 953310 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.9057. Min Act: -0.0001

Data Index: 1420636 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 1.5049. Min Range: -1.5049

Max Act: 0.8103. Min Act: -0.0001

Data Index: 1265400 (C4 (Web Text))

Max Activating Token Index: 961