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

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

Neuron 3554 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: 1651331 (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: 1179307 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 655543 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 661161 (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: 1377668 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1294505 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 757208 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 289837 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1199921 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 827961 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1417975 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1425500 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0001

Data Index: 1271895 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1541230 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 443569 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 380996 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1508299 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1431908 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1243820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1327046 (C4 (Web Text))

Max Activating Token Index: 1023