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

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

Neuron 2417 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: 0.0106. Min Range: -0.0106

Max Act: 0.0106. Min Act: -0.0002

Data Index: 805735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0086. Min Act: -0.0002

Data Index: 677599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0073. Min Act: -0.0002

Data Index: 202400 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0072. Min Act: -0.0002

Data Index: 182433 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0071. Min Act: -0.0002

Data Index: 199152 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1317064 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0067. Min Act: -0.0002

Data Index: 952544 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0065. Min Act: -0.0002

Data Index: 523499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0066. Min Act: -0.0002

Data Index: 1293784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1211825 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0062. Min Act: -0.0003

Data Index: 206120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0061. Min Act: -0.0003

Data Index: 858879 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1221435 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1081615 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1097667 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1258404 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0057. Min Act: -0.0002

Data Index: 350623 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0056. Min Act: -0.0003

Data Index: 987588 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1358650 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.0106. Min Range: -0.0106

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1330241 (C4 (Web Text))

Max Activating Token Index: 1023