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

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

Neuron 3051 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: 1.2658. Min Range: -1.2658

Max Act: 1.2658. Min Act: -0.0002

Data Index: 987234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.2286. Min Act: -0.0001

Data Index: 14307 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.2158. Min Act: -0.0001

Data Index: 496443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1994. Min Act: -0.0001

Data Index: 1108600 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1900. Min Act: -0.0001

Data Index: 335409 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1907. Min Act: -0.0001

Data Index: 921823 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1830. Min Act: -0.0001

Data Index: 467161 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1830. Min Act: -0.0001

Data Index: 144264 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1827. Min Act: -0.0001

Data Index: 175698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1723. Min Act: -0.0001

Data Index: 1043073 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1983. Min Act: -0.0001

Data Index: 105473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1990. Min Act: -0.0002

Data Index: 927071 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1772. Min Act: -0.0001

Data Index: 364698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1866. Min Act: -0.0001

Data Index: 1076847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1710. Min Act: -0.0001

Data Index: 635030 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1783. Min Act: -0.0001

Data Index: 666754 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1791. Min Act: -0.0001

Data Index: 694080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1813. Min Act: -0.0001

Data Index: 818834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1594. Min Act: -0.0001

Data Index: 394327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.2658. Min Range: -1.2658

Max Act: 1.1618. Min Act: -0.0001

Data Index: 14276 (C4 (Web Text))

Max Activating Token Index: 1023