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

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

Neuron 5032 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: 2.2081. Min Range: -2.2081

Max Act: 2.2081. Min Act: -0.0000

Data Index: 1542857 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.9972. Min Act: -0.0000

Data Index: 1528157 (Python Code)

Max Activating Token Index: 385

Text #2

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.8102. Min Act: -0.0000

Data Index: 1612151 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.7926. Min Act: -0.0000

Data Index: 1455771 (Python Code)

Max Activating Token Index: 884

Text #4

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1381776 (Python Code)

Max Activating Token Index: 679

Text #5

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.7480. Min Act: -0.0000

Data Index: 1420198 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.6648. Min Act: -0.0000

Data Index: 1581970 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.7442. Min Act: -0.0000

Data Index: 1508640 (Python Code)

Max Activating Token Index: 411

Text #8

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.6714. Min Act: -0.0000

Data Index: 252257 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.7294. Min Act: -0.0000

Data Index: 1422572 (Python Code)

Max Activating Token Index: 102

Text #10

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1389531 (Python Code)

Max Activating Token Index: 93

Text #11

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.6669. Min Act: -0.0000

Data Index: 1529141 (Python Code)

Max Activating Token Index: 263

Text #12

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1417027 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.6470. Min Act: -0.0000

Data Index: 1618757 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.5071. Min Act: -0.0000

Data Index: 1585487 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.6378. Min Act: -0.0000

Data Index: 1634047 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.4973. Min Act: -0.0000

Data Index: 1595201 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.4140. Min Act: -0.0000

Data Index: 1633100 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.6415. Min Act: -0.0000

Data Index: 1399094 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.2081. Min Range: -2.2081

Max Act: 1.6341. Min Act: -0.0000

Data Index: 1439589 (Python Code)

Max Activating Token Index: 537