Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1132. Min Act: -0.0002

Data Index: 1440059 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0003

Data Index: 1625449 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1118. Min Act: -0.0003

Data Index: 399721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1118. Min Act: 0.0001

Data Index: 1568284 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1109. Min Act: -0.0002

Data Index: 20721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1115. Min Act: -0.0004

Data Index: 254531 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1106. Min Act: 0.0000

Data Index: 1550732 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1539902 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1560808 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1452215 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1411203 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1088. Min Act: -0.0002

Data Index: 600971 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1043. Min Act: -0.0003

Data Index: 1643639 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1084. Min Act: -0.0003

Data Index: 759836 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1508018 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1081. Min Act: -0.0001

Data Index: 1639048 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1089. Min Act: -0.0002

Data Index: 832937 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1082. Min Act: -0.0003

Data Index: 1493132 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1086. Min Act: -0.0003

Data Index: 1381741 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1081. Min Act: -0.0002

Data Index: 1475353 (Python Code)

Max Activating Token Index: 1023