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

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

Neuron 2710 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4684. Min Range: -3.4684

Max Act: 3.1127. Min Act: -0.0001

Data Index: 1635602 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 3.4684. Min Range: -3.4684

Max Act: 3.4684. Min Act: -0.0000

Data Index: 1422685 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 3.4684. Min Range: -3.4684

Max Act: 3.0328. Min Act: -0.0000

Data Index: 1466478 (Python Code)

Max Activating Token Index: 563

Text #3

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.9994. Min Act: -0.0000

Data Index: 1639159 (Python Code)

Max Activating Token Index: 472

Text #4

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.9028. Min Act: -0.0001

Data Index: 1506875 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.8983. Min Act: -0.0001

Data Index: 1495004 (Python Code)

Max Activating Token Index: 897

Text #6

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.7407. Min Act: -0.0000

Data Index: 1481399 (Python Code)

Max Activating Token Index: 752

Text #7

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.7284. Min Act: -0.0001

Data Index: 1407166 (Python Code)

Max Activating Token Index: 821

Text #8

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.7003. Min Act: -0.0000

Data Index: 1404898 (Python Code)

Max Activating Token Index: 822

Text #9

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.5874. Min Act: -0.0001

Data Index: 1393925 (Python Code)

Max Activating Token Index: 649

Text #10

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.8312. Min Act: -0.0001

Data Index: 1640350 (Python Code)

Max Activating Token Index: 583

Text #11

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.8691. Min Act: -0.0000

Data Index: 1437810 (Python Code)

Max Activating Token Index: 693

Text #12

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.9729. Min Act: -0.0001

Data Index: 1652350 (Python Code)

Max Activating Token Index: 914

Text #13

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.8279. Min Act: -0.0000

Data Index: 1588145 (Python Code)

Max Activating Token Index: 828

Text #14

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.8111. Min Act: -0.0001

Data Index: 1604213 (Python Code)

Max Activating Token Index: 590

Text #15

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.6700. Min Act: -0.0000

Data Index: 1616874 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.6676. Min Act: -0.0001

Data Index: 1425213 (Python Code)

Max Activating Token Index: 822

Text #17

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.6279. Min Act: -0.0001

Data Index: 1533709 (Python Code)

Max Activating Token Index: 740

Text #18

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.6285. Min Act: -0.0000

Data Index: 1427736 (Python Code)

Max Activating Token Index: 824

Text #19

Max Range: 3.4684. Min Range: -3.4684

Max Act: 2.7432. Min Act: -0.0000

Data Index: 1503974 (Python Code)

Max Activating Token Index: 6