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

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

Neuron 4742 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: 1.8468. Min Range: -1.8468

Max Act: 1.8468. Min Act: -0.0000

Data Index: 1618683 (Python Code)

Max Activating Token Index: 404

Text #1

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.7438. Min Act: -0.0000

Data Index: 232890 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1482670 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.5988. Min Act: -0.0000

Data Index: 1473372 (Python Code)

Max Activating Token Index: 864

Text #4

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.6586. Min Act: -0.0000

Data Index: 1418871 (Python Code)

Max Activating Token Index: 100

Text #5

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1482003 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.5833. Min Act: -0.0000

Data Index: 1522449 (Python Code)

Max Activating Token Index: 619

Text #7

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.4767. Min Act: -0.0000

Data Index: 1581151 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.5051. Min Act: -0.0000

Data Index: 1554375 (Python Code)

Max Activating Token Index: 501

Text #9

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.4197. Min Act: -0.0000

Data Index: 974527 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1464146 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3974. Min Act: -0.0000

Data Index: 1396398 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3886. Min Act: -0.0000

Data Index: 1641496 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.2700. Min Act: -0.0000

Data Index: 1617131 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3779. Min Act: -0.0000

Data Index: 1621028 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3391. Min Act: -0.0000

Data Index: 1574623 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1361093 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3833. Min Act: -0.0000

Data Index: 1560717 (Python Code)

Max Activating Token Index: 452

Text #18

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1504389 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 1.8468. Min Range: -1.8468

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1628297 (Python Code)

Max Activating Token Index: 865