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

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

Neuron 3926 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6667. Min Act: -0.0000

Data Index: 1652706 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1625034 (Python Code)

Max Activating Token Index: 454

Text #2

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6471. Min Act: 0.0000

Data Index: 1635136 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6410. Min Act: -0.0000

Data Index: 845340 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1459529 (Python Code)

Max Activating Token Index: 448

Text #5

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6015. Min Act: 0.0001

Data Index: 1606969 (Python Code)

Max Activating Token Index: 476

Text #6

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5742. Min Act: -0.0000

Data Index: 713436 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1392705 (Python Code)

Max Activating Token Index: 474

Text #8

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1375233 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1403063 (Python Code)

Max Activating Token Index: 644

Text #10

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5861. Min Act: 0.0001

Data Index: 1508732 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5784. Min Act: 0.0001

Data Index: 1453934 (Python Code)

Max Activating Token Index: 324

Text #12

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5805. Min Act: -0.0000

Data Index: 190001 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1599006 (Python Code)

Max Activating Token Index: 565

Text #14

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1326070 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5579. Min Act: 0.0001

Data Index: 1472159 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5538. Min Act: 0.0000

Data Index: 1649034 (Python Code)

Max Activating Token Index: 596

Text #17

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1385071 (Python Code)

Max Activating Token Index: 990

Text #18

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5643. Min Act: -0.0000

Data Index: 129588 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.6667. Min Range: -0.6667

Max Act: 0.5440. Min Act: 0.0001

Data Index: 1428385 (Python Code)

Max Activating Token Index: 349