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

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

Neuron 151 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: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0006

Data Index: 607417 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0123. Min Act: -0.0006

Data Index: 168265 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0121. Min Act: -0.0006

Data Index: 486528 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0113. Min Act: -0.0006

Data Index: 474240 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0110. Min Act: -0.0006

Data Index: 700481 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1547664 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0105. Min Act: -0.0006

Data Index: 918921 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0109. Min Act: -0.0006

Data Index: 1096045 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1160130 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0100. Min Act: -0.0006

Data Index: 758542 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1150972 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0103. Min Act: -0.0006

Data Index: 808868 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0098. Min Act: -0.0006

Data Index: 885529 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1584720 (Python Code)

Max Activating Token Index: 925

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0099. Min Act: -0.0006

Data Index: 80791 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0097. Min Act: -0.0006

Data Index: 897776 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0098. Min Act: -0.0006

Data Index: 171142 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0097. Min Act: -0.0006

Data Index: 45480 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0095. Min Act: -0.0006

Data Index: 17100 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0093. Min Act: -0.0006

Data Index: 823553 (C4 (Web Text))

Max Activating Token Index: 1023