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

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

Neuron 2238 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1696. Min Act: -0.0003

Data Index: 779403 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1634. Min Act: -0.0003

Data Index: 214425 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1615. Min Act: -0.0003

Data Index: 657942 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1666. Min Act: -0.0003

Data Index: 1268303 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1661. Min Act: -0.0003

Data Index: 312506 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1569. Min Act: -0.0003

Data Index: 482042 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1624. Min Act: -0.0003

Data Index: 374937 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1605. Min Act: -0.0003

Data Index: 282331 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1609. Min Act: -0.0003

Data Index: 842705 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1492. Min Act: -0.0003

Data Index: 458199 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1598. Min Act: -0.0003

Data Index: 1261136 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1452. Min Act: -0.0003

Data Index: 312735 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1655. Min Act: -0.0003

Data Index: 164303 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1552. Min Act: -0.0003

Data Index: 996082 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1606. Min Act: -0.0003

Data Index: 730736 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1473. Min Act: -0.0003

Data Index: 238838 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1524. Min Act: -0.0003

Data Index: 385270 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1525. Min Act: -0.0003

Data Index: 400201 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1565. Min Act: -0.0003

Data Index: 974589 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.1696. Min Range: -0.1696

Max Act: 0.1408. Min Act: -0.0003

Data Index: 836603 (C4 (Web Text))

Max Activating Token Index: 283