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

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

Neuron 1561 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: 0.2947. Min Range: -0.2947

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1456980 (Python Code)

Max Activating Token Index: 422

Text #1

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1451272 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1443687 (Python Code)

Max Activating Token Index: 435

Text #3

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1489725 (Python Code)

Max Activating Token Index: 908

Text #4

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1615135 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1548338 (Python Code)

Max Activating Token Index: 780

Text #6

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1459758 (Python Code)

Max Activating Token Index: 724

Text #7

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1442618 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1511965 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2362. Min Act: -0.0000

Data Index: 1400242 (Python Code)

Max Activating Token Index: 278

Text #10

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1391585 (Python Code)

Max Activating Token Index: 340

Text #11

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1972. Min Act: -0.0000

Data Index: 190873 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1520578 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1642971 (Python Code)

Max Activating Token Index: 738

Text #14

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1559807 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1896. Min Act: -0.0000

Data Index: 657437 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1483374 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1926. Min Act: -0.0000

Data Index: 1423904 (Python Code)

Max Activating Token Index: 509

Text #18

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1710. Min Act: -0.0000

Data Index: 941989 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 0.2947. Min Range: -0.2947

Max Act: 0.1673. Min Act: -0.0000

Data Index: 322006 (C4 (Web Text))

Max Activating Token Index: 696