Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1042 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.2072. Min Act: -0.0001

Data Index: 301070 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.2068. Min Act: -0.0001

Data Index: 160966 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1823. Min Act: -0.0001

Data Index: 787591 (C4 (Web Text))

Max Activating Token Index: 1013

Text #3

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1704. Min Act: -0.0001

Data Index: 1338031 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1677. Min Act: -0.0001

Data Index: 1171094 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1674. Min Act: -0.0001

Data Index: 416140 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1282720 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1701. Min Act: -0.0001

Data Index: 580905 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1537. Min Act: -0.0001

Data Index: 67387 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1525. Min Act: -0.0000

Data Index: 682684 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1595. Min Act: -0.0001

Data Index: 609435 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1643. Min Act: -0.0001

Data Index: 631155 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1502. Min Act: -0.0001

Data Index: 415989 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1524. Min Act: -0.0001

Data Index: 819959 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1522. Min Act: -0.0001

Data Index: 967584 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1565. Min Act: -0.0001

Data Index: 942259 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1289401 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1554. Min Act: -0.0000

Data Index: 98125 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1518. Min Act: -0.0001

Data Index: 109797 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.2072. Min Range: -0.2072

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1323900 (C4 (Web Text))

Max Activating Token Index: 574