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

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

Neuron 518 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0658. Min Range: -1.0658

Max Act: 1.0070. Min Act: -0.0002

Data Index: 1424814 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 1.0658. Min Range: -1.0658

Max Act: 1.0658. Min Act: -0.0002

Data Index: 1603195 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9395. Min Act: -0.0002

Data Index: 1539421 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9553. Min Act: -0.0002

Data Index: 1413467 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9484. Min Act: -0.0002

Data Index: 1433820 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9165. Min Act: -0.0002

Data Index: 1602291 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9799. Min Act: -0.0002

Data Index: 1433533 (Python Code)

Max Activating Token Index: 555

Text #7

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9304. Min Act: -0.0002

Data Index: 1533865 (Python Code)

Max Activating Token Index: 314

Text #8

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9055. Min Act: -0.0002

Data Index: 1372052 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9272. Min Act: -0.0002

Data Index: 1406787 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.9475. Min Act: -0.0002

Data Index: 1453052 (Python Code)

Max Activating Token Index: 730

Text #11

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8657. Min Act: -0.0002

Data Index: 1439359 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8129. Min Act: -0.0002

Data Index: 1600740 (Python Code)

Max Activating Token Index: 275

Text #13

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8505. Min Act: -0.0002

Data Index: 1454489 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8504. Min Act: -0.0002

Data Index: 1490645 (Python Code)

Max Activating Token Index: 646

Text #15

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8794. Min Act: -0.0002

Data Index: 1654350 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.7906. Min Act: -0.0002

Data Index: 1608001 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8681. Min Act: -0.0002

Data Index: 1453848 (Python Code)

Max Activating Token Index: 754

Text #18

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8946. Min Act: -0.0002

Data Index: 1538815 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 1.0658. Min Range: -1.0658

Max Act: 0.8665. Min Act: -0.0002

Data Index: 1630799 (Python Code)

Max Activating Token Index: 11