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

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

Neuron 5241 in Layer 1

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: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1409887 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 403111 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1241874 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1012663 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 630629 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1022296 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1467577 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1230424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1442226 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1510471 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 543560 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1643103 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1542844 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1258249 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1547875 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1501556 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1520417 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1402944 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 877228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1600345 (Python Code)

Max Activating Token Index: 1023