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

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

Neuron 1307 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1338004 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0146. Min Act: -0.0006

Data Index: 151562 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0143. Min Act: -0.0006

Data Index: 843535 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0139. Min Act: -0.0006

Data Index: 97243 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0136. Min Act: -0.0006

Data Index: 238122 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1290937 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1346190 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0130. Min Act: -0.0006

Data Index: 890571 (C4 (Web Text))

Max Activating Token Index: 177

Text #8

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0128. Min Act: -0.0006

Data Index: 546505 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0125. Min Act: -0.0006

Data Index: 891512 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0125. Min Act: -0.0006

Data Index: 27466 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0125. Min Act: -0.0006

Data Index: 63845 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0123. Min Act: -0.0006

Data Index: 666143 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0118. Min Act: -0.0006

Data Index: 900003 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0121. Min Act: -0.0007

Data Index: 816983 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0121. Min Act: -0.0006

Data Index: 294908 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1106218 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1014792 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1109757 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0117. Min Act: -0.0006

Data Index: 188946 (C4 (Web Text))

Max Activating Token Index: 866