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

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

Neuron 2627 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: 0.3087. Min Range: -0.3087

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1075755 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2313. Min Act: -0.0000

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1120740 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1979. Min Act: -0.0000

Data Index: 896896 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1867. Min Act: -0.0000

Data Index: 65723 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1771. Min Act: -0.0000

Data Index: 788095 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1829. Min Act: -0.0000

Data Index: 4047 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1730. Min Act: -0.0000

Data Index: 437121 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1168048 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1742. Min Act: -0.0000

Data Index: 511793 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1727. Min Act: -0.0000

Data Index: 650501 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1586. Min Act: -0.0000

Data Index: 568529 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1643. Min Act: -0.0000

Data Index: 871361 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1632. Min Act: -0.0000

Data Index: 641237 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1570. Min Act: -0.0000

Data Index: 114660 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1567. Min Act: 0.0000

Data Index: 118699 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1545. Min Act: -0.0000

Data Index: 630339 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1636. Min Act: -0.0000

Data Index: 193756 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1510. Min Act: -0.0000

Data Index: 1301435 (C4 (Web Text))

Max Activating Token Index: 588

Text #19

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1502. Min Act: -0.0000

Data Index: 639315 (C4 (Web Text))

Max Activating Token Index: 677