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

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

Neuron 189 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: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0005

Data Index: 780134 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0130. Min Act: -0.0005

Data Index: 974593 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0133. Min Act: -0.0005

Data Index: 1561157 (Python Code)

Max Activating Token Index: 203

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1527010 (Python Code)

Max Activating Token Index: 785

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1258596 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0129. Min Act: -0.0005

Data Index: 30405 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0127. Min Act: -0.0006

Data Index: 284396 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0125. Min Act: -0.0005

Data Index: 673398 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0006

Data Index: 760157 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1540231 (Python Code)

Max Activating Token Index: 953

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0005

Data Index: 1233163 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0118. Min Act: -0.0006

Data Index: 788909 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0005

Data Index: 432534 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0119. Min Act: -0.0005

Data Index: 648489 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0121. Min Act: -0.0005

Data Index: 866634 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1289955 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0005

Data Index: 845210 (C4 (Web Text))

Max Activating Token Index: 635

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0005

Data Index: 981724 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0006

Data Index: 924401 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1499346 (Python Code)

Max Activating Token Index: 790