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

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

Neuron 229 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.9525. Min Act: -0.0001

Data Index: 1532084 (Python Code)

Max Activating Token Index: 691

Text #1

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8605. Min Act: -0.0001

Data Index: 1445073 (Python Code)

Max Activating Token Index: 1016

Text #2

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8666. Min Act: -0.0001

Data Index: 1469902 (Python Code)

Max Activating Token Index: 694

Text #3

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7530. Min Act: -0.0001

Data Index: 1582505 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8336. Min Act: -0.0001

Data Index: 1621781 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.8050. Min Act: -0.0001

Data Index: 1478235 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7200. Min Act: -0.0001

Data Index: 1531880 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7396. Min Act: -0.0001

Data Index: 1516800 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1417872 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6987. Min Act: -0.0001

Data Index: 1469220 (Python Code)

Max Activating Token Index: 335

Text #10

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7144. Min Act: -0.0001

Data Index: 1537446 (Python Code)

Max Activating Token Index: 387

Text #11

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6971. Min Act: -0.0001

Data Index: 1557046 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6897. Min Act: -0.0001

Data Index: 1518118 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6899. Min Act: -0.0001

Data Index: 1552029 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6774. Min Act: -0.0001

Data Index: 1601889 (Python Code)

Max Activating Token Index: 186

Text #15

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6760. Min Act: -0.0001

Data Index: 1493709 (Python Code)

Max Activating Token Index: 819

Text #16

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6596. Min Act: -0.0001

Data Index: 1410101 (Python Code)

Max Activating Token Index: 225

Text #17

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.5859. Min Act: -0.0001

Data Index: 1505903 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.6668. Min Act: -0.0001

Data Index: 1445379 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 0.9525. Min Range: -0.9525

Max Act: 0.7052. Min Act: -0.0001

Data Index: 1469233 (Python Code)

Max Activating Token Index: 263