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

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

Neuron 6006 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: 0.0026. Min Range: -0.0026

Max Act: 0.0026. Min Act: -0.0002

Data Index: 423802 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0022. Min Act: -0.0002

Data Index: 977798 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0021. Min Act: -0.0002

Data Index: 304225 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0020. Min Act: -0.0002

Data Index: 1299723 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 880591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 205329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 780692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0019. Min Act: -0.0002

Data Index: 242933 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0002

Data Index: 710215 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0002

Data Index: 13700 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0002

Data Index: 575912 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0002

Data Index: 297616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0002

Data Index: 1482317 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0017. Min Act: -0.0002

Data Index: 329377 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0016. Min Act: -0.0002

Data Index: 589487 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0016. Min Act: -0.0002

Data Index: 227987 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0016. Min Act: -0.0002

Data Index: 263394 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0016. Min Act: -0.0002

Data Index: 558681 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1048356 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0026. Min Range: -0.0026

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1003939 (C4 (Web Text))

Max Activating Token Index: 622