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

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

Neuron 5226 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: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1084056 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1268477 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1538372 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0063. Min Act: -0.0002

Data Index: 913224 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0061. Min Act: -0.0002

Data Index: 519535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0056. Min Act: -0.0002

Data Index: 429047 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0055. Min Act: -0.0002

Data Index: 653683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1638868 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0055. Min Act: -0.0002

Data Index: 44633 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0054. Min Act: -0.0002

Data Index: 242176 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1411087 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1124696 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0052. Min Act: -0.0002

Data Index: 738921 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0052. Min Act: -0.0002

Data Index: 527451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1434773 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1534314 (Python Code)

Max Activating Token Index: 960

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1203522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0050. Min Act: -0.0002

Data Index: 1240797 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0049. Min Act: -0.0002

Data Index: 1573690 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0050. Min Act: -0.0002

Data Index: 215436 (C4 (Web Text))

Max Activating Token Index: 1023