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

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

Neuron 853 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: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0005

Data Index: 985788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0198. Min Act: -0.0005

Data Index: 1556012 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0147. Min Act: -0.0006

Data Index: 650453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1575383 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0132. Min Act: -0.0005

Data Index: 465530 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0130. Min Act: -0.0005

Data Index: 1612868 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0124. Min Act: -0.0006

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1635546 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0128. Min Act: -0.0006

Data Index: 575717 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0119. Min Act: -0.0005

Data Index: 1598417 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0113. Min Act: -0.0006

Data Index: 780933 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1591930 (Python Code)

Max Activating Token Index: 972

Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0113. Min Act: -0.0006

Data Index: 581659 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0111. Min Act: -0.0006

Data Index: 745496 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1469663 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0108. Min Act: -0.0006

Data Index: 170549 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0108. Min Act: -0.0006

Data Index: 339797 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1262811 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0104. Min Act: -0.0006

Data Index: 843826 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1067027 (C4 (Web Text))

Max Activating Token Index: 1020