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

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

Neuron 2429 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: 3.7893. Min Range: -3.7893

Max Act: 3.6211. Min Act: -0.0000

Data Index: 1482100 (Python Code)

Max Activating Token Index: 521

Text #1

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.7893. Min Act: -0.0000

Data Index: 1560630 (Python Code)

Max Activating Token Index: 633

Text #2

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3401. Min Act: -0.0000

Data Index: 1406193 (Python Code)

Max Activating Token Index: 140

Text #3

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3108. Min Act: -0.0000

Data Index: 1584379 (Python Code)

Max Activating Token Index: 693

Text #4

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.3079. Min Act: -0.0000

Data Index: 1423366 (Python Code)

Max Activating Token Index: 497

Text #5

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.1822. Min Act: -0.0000

Data Index: 1437525 (Python Code)

Max Activating Token Index: 912

Text #6

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.0129. Min Act: -0.0000

Data Index: 1580511 (Python Code)

Max Activating Token Index: 659

Text #7

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.9855. Min Act: -0.0000

Data Index: 1370473 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.9022. Min Act: -0.0000

Data Index: 1513566 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.0294. Min Act: -0.0000

Data Index: 1459966 (Python Code)

Max Activating Token Index: 966

Text #10

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.0304. Min Act: -0.0000

Data Index: 1412167 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.1249. Min Act: -0.0000

Data Index: 1402226 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.9705. Min Act: -0.0000

Data Index: 1517002 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.9680. Min Act: -0.0000

Data Index: 1494438 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.8251. Min Act: -0.0000

Data Index: 1460219 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 3.7893. Min Range: -3.7893

Max Act: 3.1089. Min Act: -0.0000

Data Index: 1556540 (Python Code)

Max Activating Token Index: 603

Text #16

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.7870. Min Act: -0.0000

Data Index: 1450159 (Python Code)

Max Activating Token Index: 845

Text #17

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.9179. Min Act: -0.0000

Data Index: 1373042 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.8667. Min Act: -0.0000

Data Index: 1452799 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 3.7893. Min Range: -3.7893

Max Act: 2.9562. Min Act: -0.0000

Data Index: 1475945 (Python Code)

Max Activating Token Index: 48