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

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

Neuron 4618 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1786. Min Act: -0.0000

Data Index: 1551254 (Python Code)

Max Activating Token Index: 547

Text #1

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0618. Min Act: -0.0000

Data Index: 606247 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0701. Min Act: -0.0000

Data Index: 290848 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1592284 (Python Code)

Max Activating Token Index: 759

Text #4

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1647892 (Python Code)

Max Activating Token Index: 463

Text #5

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1459083 (Python Code)

Max Activating Token Index: 931

Text #6

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1562929 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7304. Min Act: -0.0000

Data Index: 1572024 (Python Code)

Max Activating Token Index: 77

Text #8

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7225. Min Act: -0.0000

Data Index: 896725 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6858. Min Act: -0.0000

Data Index: 525738 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1465488 (Python Code)

Max Activating Token Index: 383

Text #11

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.7229. Min Act: -0.0000

Data Index: 497079 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6941. Min Act: -0.0000

Data Index: 595109 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1610495 (Python Code)

Max Activating Token Index: 610

Text #14

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6816. Min Act: -0.0000

Data Index: 570413 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1576738 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6650. Min Act: -0.0000

Data Index: 86382 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6573. Min Act: -0.0000

Data Index: 319922 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1186864 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.1786. Min Range: -1.1786

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1473822 (Python Code)

Max Activating Token Index: 123