Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1926 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0157. Min Act: -0.0005

Data Index: 779489 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0145. Min Act: -0.0005

Data Index: 913701 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0144. Min Act: -0.0005

Data Index: 1561449 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0135. Min Act: -0.0005

Data Index: 227896 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1345916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0005

Data Index: 254701 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0127. Min Act: -0.0005

Data Index: 1569596 (Python Code)

Max Activating Token Index: 269

Text #7

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0125. Min Act: -0.0005

Data Index: 42144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0124. Min Act: -0.0005

Data Index: 476258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0005

Data Index: 726398 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0120. Min Act: -0.0005

Data Index: 420491 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0118. Min Act: -0.0005

Data Index: 1419652 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1384480 (Python Code)

Max Activating Token Index: 578

Text #13

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1554517 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0114. Min Act: -0.0005

Data Index: 388942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1391401 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0115. Min Act: -0.0005

Data Index: 800287 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0110. Min Act: -0.0005

Data Index: 1189405 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0110. Min Act: -0.0005

Data Index: 1547910 (Python Code)

Max Activating Token Index: 419

Text #19

Max Range: 0.0157. Min Range: -0.0157

Max Act: 0.0112. Min Act: -0.0005

Data Index: 573558 (C4 (Web Text))

Max Activating Token Index: 918