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

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

Neuron 2869 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: 0.3806. Min Range: -0.3806

Max Act: 0.3806. Min Act: -0.0001

Data Index: 1406291 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1628272 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3170. Min Act: -0.0001

Data Index: 1597502 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3093. Min Act: -0.0001

Data Index: 1628590 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3144. Min Act: -0.0001

Data Index: 1584415 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3131. Min Act: -0.0001

Data Index: 1518995 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3086. Min Act: -0.0001

Data Index: 1636405 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3068. Min Act: -0.0001

Data Index: 1495449 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1454092 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1490590 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2955. Min Act: -0.0002

Data Index: 1405891 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1541026 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2903. Min Act: -0.0001

Data Index: 1388997 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2904. Min Act: -0.0001

Data Index: 1521629 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1555162 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1379525 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1513676 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2799. Min Act: -0.0001

Data Index: 1500657 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1380598 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.3806. Min Range: -0.3806

Max Act: 0.2812. Min Act: -0.0001

Data Index: 1380264 (Python Code)

Max Activating Token Index: 1023