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

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

Neuron 1222 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: 0.1206. Min Range: -0.1206

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1285341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1123. Min Act: -0.0001

Data Index: 660988 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1075. Min Act: -0.0001

Data Index: 21231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1066. Min Act: -0.0001

Data Index: 641934 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1048. Min Act: -0.0001

Data Index: 933707 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1067. Min Act: -0.0001

Data Index: 909542 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1021. Min Act: -0.0001

Data Index: 78140 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0982. Min Act: -0.0001

Data Index: 758678 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0981. Min Act: -0.0001

Data Index: 220927 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0999. Min Act: -0.0001

Data Index: 72259 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.1007. Min Act: -0.0001

Data Index: 559995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0983. Min Act: -0.0001

Data Index: 207671 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0981. Min Act: -0.0001

Data Index: 933318 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0975. Min Act: -0.0001

Data Index: 897256 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0979. Min Act: -0.0001

Data Index: 609913 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0959. Min Act: -0.0001

Data Index: 236646 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0954. Min Act: -0.0001

Data Index: 842227 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0959. Min Act: -0.0001

Data Index: 651018 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0955. Min Act: -0.0001

Data Index: 875472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1206. Min Range: -0.1206

Max Act: 0.0951. Min Act: -0.0001

Data Index: 704048 (C4 (Web Text))

Max Activating Token Index: 768