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

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

Neuron 1902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2715. Min Range: -4.2715

Max Act: 4.2715. Min Act: -0.0000

Data Index: 1602512 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 4.2715. Min Range: -4.2715

Max Act: 3.3624. Min Act: -0.0000

Data Index: 1552875 (Python Code)

Max Activating Token Index: 894

Text #2

Max Range: 4.2715. Min Range: -4.2715

Max Act: 3.3358. Min Act: -0.0000

Data Index: 1652313 (Python Code)

Max Activating Token Index: 631

Text #3

Max Range: 4.2715. Min Range: -4.2715

Max Act: 3.4372. Min Act: -0.0000

Data Index: 1420201 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.9616. Min Act: -0.0000

Data Index: 1587257 (Python Code)

Max Activating Token Index: 540

Text #5

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.8945. Min Act: -0.0000

Data Index: 1394024 (Python Code)

Max Activating Token Index: 361

Text #6

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.8589. Min Act: -0.0000

Data Index: 1479492 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.7028. Min Act: -0.0000

Data Index: 1637661 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.6939. Min Act: -0.0000

Data Index: 1562780 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.5867. Min Act: -0.0000

Data Index: 1596128 (Python Code)

Max Activating Token Index: 530

Text #10

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.5765. Min Act: -0.0000

Data Index: 1519853 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.5585. Min Act: -0.0000

Data Index: 1640628 (Python Code)

Max Activating Token Index: 238

Text #12

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.2810. Min Act: -0.0000

Data Index: 1521639 (Python Code)

Max Activating Token Index: 623

Text #13

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.4101. Min Act: -0.0000

Data Index: 1503652 (Python Code)

Max Activating Token Index: 730

Text #14

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.6470. Min Act: -0.0000

Data Index: 1510483 (Python Code)

Max Activating Token Index: 270

Text #15

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.4295. Min Act: -0.0000

Data Index: 1359860 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.4095. Min Act: -0.0000

Data Index: 1383017 (Python Code)

Max Activating Token Index: 497

Text #17

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.1532. Min Act: -0.0000

Data Index: 1428957 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1368549 (Python Code)

Max Activating Token Index: 366

Text #19

Max Range: 4.2715. Min Range: -4.2715

Max Act: 2.1804. Min Act: -0.0000

Data Index: 1402926 (Python Code)

Max Activating Token Index: 95