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

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

Neuron 688 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0006

Data Index: 456803 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1128820 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0085. Min Act: -0.0006

Data Index: 266305 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0087. Min Act: -0.0006

Data Index: 513191 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0083. Min Act: -0.0006

Data Index: 180423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0006

Data Index: 709043 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1113368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1532519 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0084. Min Act: -0.0006

Data Index: 365311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0082. Min Act: -0.0006

Data Index: 728217 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1172490 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1110456 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1017605 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0079. Min Act: -0.0006

Data Index: 241169 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1449860 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0079. Min Act: -0.0006

Data Index: 423015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0079. Min Act: -0.0006

Data Index: 113141 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1139249 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0079. Min Act: -0.0006

Data Index: 696226 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0077. Min Act: -0.0006

Data Index: 62197 (C4 (Web Text))

Max Activating Token Index: 659