Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1738 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1393070 (Python Code)

Max Activating Token Index: 80

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0895. Min Act: -0.0003

Data Index: 1378973 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0884. Min Act: -0.0003

Data Index: 1370536 (Python Code)

Max Activating Token Index: 14

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0874. Min Act: -0.0003

Data Index: 1501255 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1537176 (Python Code)

Max Activating Token Index: 752

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0873. Min Act: -0.0003

Data Index: 1501628 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0836. Min Act: -0.0003

Data Index: 1528221 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0841. Min Act: -0.0003

Data Index: 1531564 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1591667 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1412797 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1576715 (Python Code)

Max Activating Token Index: 73

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1533751 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0831. Min Act: -0.0003

Data Index: 1601803 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0817. Min Act: -0.0003

Data Index: 1506033 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1452500 (Python Code)

Max Activating Token Index: 56

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1429863 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1497674 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0829. Min Act: -0.0003

Data Index: 1512586 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0816. Min Act: -0.0003

Data Index: 1371706 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0804. Min Act: -0.0003

Data Index: 1472809 (Python Code)

Max Activating Token Index: 23