Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2543 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1454678 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0127. Min Act: -0.0000

Data Index: 1526280 (Python Code)

Max Activating Token Index: 899

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1010886 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0628. Min Act: -0.0000

Data Index: 588021 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0547. Min Act: -0.0000

Data Index: 38102 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0630. Min Act: -0.0000

Data Index: 429469 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0586. Min Act: -0.0000

Data Index: 272095 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0666. Min Act: -0.0000

Data Index: 793758 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0510. Min Act: -0.0000

Data Index: 542692 (C4 (Web Text))

Max Activating Token Index: 193

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0585. Min Act: -0.0000

Data Index: 465445 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1233 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1178065 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0668. Min Act: -0.0000

Data Index: 513125 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0578. Min Act: -0.0000

Data Index: 570122 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1405119 (Python Code)

Max Activating Token Index: 953

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0476. Min Act: -0.0000

Data Index: 490783 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1451379 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0522. Min Act: -0.0000

Data Index: 399599 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0462. Min Act: -0.0000

Data Index: 170945 (C4 (Web Text))

Max Activating Token Index: 241

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0507. Min Act: -0.0000

Data Index: 432877 (C4 (Web Text))

Max Activating Token Index: 844