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

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

Neuron 1434 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: 4.9696. Min Range: -4.9696

Max Act: 4.9696. Min Act: -0.0000

Data Index: 1591728 (Python Code)

Max Activating Token Index: 850

Text #1

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.5738. Min Act: -0.0000

Data Index: 1389209 (Python Code)

Max Activating Token Index: 207

Text #2

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.6961. Min Act: -0.0000

Data Index: 1547770 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.4532. Min Act: -0.0000

Data Index: 1633358 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.5013. Min Act: -0.0000

Data Index: 1438332 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.2543. Min Act: -0.0000

Data Index: 1508178 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.9431. Min Act: -0.0000

Data Index: 1390493 (Python Code)

Max Activating Token Index: 952

Text #7

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.8149. Min Act: -0.0000

Data Index: 1415786 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 4.9696. Min Range: -4.9696

Max Act: 4.0413. Min Act: -0.0000

Data Index: 1617070 (Python Code)

Max Activating Token Index: 350

Text #9

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.8214. Min Act: -0.0000

Data Index: 1461156 (Python Code)

Max Activating Token Index: 1018

Text #10

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.8608. Min Act: -0.0000

Data Index: 1620315 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.6252. Min Act: -0.0000

Data Index: 1562080 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.8273. Min Act: -0.0000

Data Index: 1560887 (Python Code)

Max Activating Token Index: 586

Text #13

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.6151. Min Act: -0.0000

Data Index: 1558953 (Python Code)

Max Activating Token Index: 340

Text #14

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.5320. Min Act: -0.0000

Data Index: 1633416 (Python Code)

Max Activating Token Index: 704

Text #15

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.5312. Min Act: -0.0000

Data Index: 1615679 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.4837. Min Act: -0.0000

Data Index: 1389403 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.3030. Min Act: -0.0000

Data Index: 1454270 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.3566. Min Act: -0.0000

Data Index: 1595769 (Python Code)

Max Activating Token Index: 563

Text #19

Max Range: 4.9696. Min Range: -4.9696

Max Act: 3.5264. Min Act: -0.0000

Data Index: 1429455 (Python Code)

Max Activating Token Index: 935