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

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

Neuron 180 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: 0.0160. Min Range: -0.0160

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1068159 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0160. Min Act: -0.0006

Data Index: 538212 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0136. Min Act: -0.0006

Data Index: 91841 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0133. Min Act: -0.0006

Data Index: 204351 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0131. Min Act: -0.0006

Data Index: 269282 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0128. Min Act: -0.0006

Data Index: 447373 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0128. Min Act: -0.0006

Data Index: 1008999 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1224692 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1227774 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0123. Min Act: -0.0006

Data Index: 621764 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0125. Min Act: -0.0006

Data Index: 204551 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0124. Min Act: -0.0006

Data Index: 101152 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1207287 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1155597 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0006

Data Index: 322630 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0122. Min Act: -0.0006

Data Index: 790002 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0119. Min Act: -0.0006

Data Index: 603799 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0120. Min Act: -0.0006

Data Index: 263504 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0117. Min Act: -0.0006

Data Index: 66183 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0160. Min Range: -0.0160

Max Act: 0.0114. Min Act: -0.0006

Data Index: 478945 (C4 (Web Text))

Max Activating Token Index: 698