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

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

Neuron 2665 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: 0.9186. Min Range: -0.9186

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1392756 (Python Code)

Max Activating Token Index: 324

Text #1

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9109. Min Act: -0.0001

Data Index: 1535529 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8886. Min Act: -0.0001

Data Index: 1479769 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1649209 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8816. Min Act: -0.0001

Data Index: 1402960 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8896. Min Act: -0.0001

Data Index: 1471472 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8846. Min Act: -0.0001

Data Index: 1569624 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8704. Min Act: -0.0001

Data Index: 1477230 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8701. Min Act: -0.0001

Data Index: 1463893 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1652033 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8581. Min Act: -0.0001

Data Index: 1483491 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8622. Min Act: -0.0001

Data Index: 1388401 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8629. Min Act: -0.0001

Data Index: 1606880 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8457. Min Act: -0.0001

Data Index: 1557747 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8588. Min Act: -0.0001

Data Index: 1528371 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8527. Min Act: -0.0001

Data Index: 1529227 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1625673 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8371. Min Act: -0.0001

Data Index: 1612481 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8364. Min Act: -0.0002

Data Index: 1610412 (Python Code)

Max Activating Token Index: 139

Text #19

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.8418. Min Act: -0.0002

Data Index: 1402639 (Python Code)

Max Activating Token Index: 1023