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

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

Neuron 2712 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.1704. Min Act: -0.0001

Data Index: 1493157 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.1704. Min Range: -1.1704

Max Act: 1.0780. Min Act: -0.0001

Data Index: 1465413 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9807. Min Act: -0.0001

Data Index: 1574691 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1386195 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8913. Min Act: -0.0001

Data Index: 1376468 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8975. Min Act: -0.0001

Data Index: 1521910 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8748. Min Act: -0.0001

Data Index: 1400709 (Python Code)

Max Activating Token Index: 769

Text #7

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8723. Min Act: -0.0001

Data Index: 1383428 (Python Code)

Max Activating Token Index: 35

Text #8

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8426. Min Act: -0.0001

Data Index: 1416522 (Python Code)

Max Activating Token Index: 866

Text #9

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8499. Min Act: -0.0001

Data Index: 1623591 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8424. Min Act: -0.0001

Data Index: 1370743 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8339. Min Act: -0.0001

Data Index: 1533417 (Python Code)

Max Activating Token Index: 911

Text #12

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8169. Min Act: -0.0001

Data Index: 1455799 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8062. Min Act: -0.0001

Data Index: 1413387 (Python Code)

Max Activating Token Index: 975

Text #14

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8165. Min Act: -0.0001

Data Index: 1555739 (Python Code)

Max Activating Token Index: 870

Text #15

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1619417 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7890. Min Act: -0.0001

Data Index: 1519100 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7775. Min Act: -0.0001

Data Index: 1465676 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1633781 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 1.1704. Min Range: -1.1704

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1462528 (Python Code)

Max Activating Token Index: 68