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

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

Neuron 3666 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8906. Min Act: -0.0000

Data Index: 251805 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8399. Min Act: -0.0000

Data Index: 1557055 (Python Code)

Max Activating Token Index: 549

Text #2

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8326. Min Act: -0.0000

Data Index: 432241 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1586254 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1477419 (Python Code)

Max Activating Token Index: 528

Text #5

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8092. Min Act: -0.0000

Data Index: 862795 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7770. Min Act: -0.0000

Data Index: 985026 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7896. Min Act: -0.0000

Data Index: 770426 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1520403 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7681. Min Act: -0.0000

Data Index: 801454 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.8094. Min Act: -0.0000

Data Index: 1378834 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1375040 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1397871 (Python Code)

Max Activating Token Index: 390

Text #13

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7747. Min Act: -0.0000

Data Index: 200154 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7674. Min Act: -0.0000

Data Index: 1258779 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1092188 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1347284 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1101009 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1271806 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.8906. Min Range: -0.8906

Max Act: 0.7268. Min Act: -0.0000

Data Index: 496371 (C4 (Web Text))

Max Activating Token Index: 929