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

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

Neuron 1210 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1999. Min Act: -0.0001

Data Index: 457749 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1062281 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1846. Min Act: -0.0001

Data Index: 967143 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1860. Min Act: -0.0001

Data Index: 958864 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1830. Min Act: -0.0001

Data Index: 366266 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1638. Min Act: -0.0001

Data Index: 342001 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1562. Min Act: -0.0001

Data Index: 500535 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1729. Min Act: -0.0001

Data Index: 847316 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1731. Min Act: -0.0001

Data Index: 1208197 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1171312 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1606. Min Act: -0.0001

Data Index: 985517 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1591. Min Act: -0.0001

Data Index: 712378 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1077382 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1584. Min Act: -0.0001

Data Index: 843430 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1708. Min Act: -0.0001

Data Index: 313268 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1083447 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1689. Min Act: -0.0001

Data Index: 444634 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1092330 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1631. Min Act: -0.0001

Data Index: 219330 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1563. Min Act: -0.0001

Data Index: 227318 (C4 (Web Text))

Max Activating Token Index: 132