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

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

Neuron 778 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: 0.8451. Min Range: -0.8451

Max Act: 0.8451. Min Act: -0.0001

Data Index: 547554 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8261. Min Act: -0.0001

Data Index: 833112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8214. Min Act: -0.0001

Data Index: 807309 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8202. Min Act: -0.0001

Data Index: 1052938 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1031362 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8107. Min Act: -0.0001

Data Index: 701280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8046. Min Act: -0.0002

Data Index: 1326270 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7939. Min Act: -0.0001

Data Index: 92367 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8051. Min Act: -0.0001

Data Index: 1294950 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7979. Min Act: -0.0001

Data Index: 739417 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7895. Min Act: -0.0001

Data Index: 619593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7962. Min Act: -0.0001

Data Index: 1256304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7899. Min Act: -0.0001

Data Index: 729214 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7941. Min Act: -0.0001

Data Index: 29299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7984. Min Act: -0.0001

Data Index: 859873 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8033. Min Act: -0.0001

Data Index: 634152 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7911. Min Act: -0.0002

Data Index: 487464 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7900. Min Act: -0.0001

Data Index: 848943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7815. Min Act: -0.0001

Data Index: 184846 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7836. Min Act: -0.0001

Data Index: 896034 (C4 (Web Text))

Max Activating Token Index: 1023