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

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

Neuron 4715 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.5294. Min Act: -0.0000

Data Index: 1370842 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1470693 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3487. Min Act: -0.0000

Data Index: 1374680 (Python Code)

Max Activating Token Index: 149

Text #3

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1424079 (Python Code)

Max Activating Token Index: 93

Text #4

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2819. Min Act: -0.0000

Data Index: 1419959 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1603913 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1610716 (Python Code)

Max Activating Token Index: 778

Text #7

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1614523 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2035. Min Act: -0.0000

Data Index: 1508237 (Python Code)

Max Activating Token Index: 462

Text #9

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1631481 (Python Code)

Max Activating Token Index: 167

Text #10

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1550742 (Python Code)

Max Activating Token Index: 136

Text #11

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1611591 (Python Code)

Max Activating Token Index: 116

Text #12

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1535199 (Python Code)

Max Activating Token Index: 411

Text #13

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.1855. Min Act: -0.0000

Data Index: 1573820 (Python Code)

Max Activating Token Index: 474

Text #14

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1396762 (Python Code)

Max Activating Token Index: 155

Text #15

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0799. Min Act: -0.0000

Data Index: 1375096 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9987. Min Act: -0.0000

Data Index: 1457161 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1427683 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 1.5510. Min Range: -1.5510

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1604697 (Python Code)

Max Activating Token Index: 773

Text #19

Max Range: 1.5510. Min Range: -1.5510

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1627460 (Python Code)

Max Activating Token Index: 26