Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2276 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0004

Data Index: 26734 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0154. Min Act: -0.0004

Data Index: 1155933 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0160. Min Act: -0.0004

Data Index: 449928 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0132. Min Act: -0.0004

Data Index: 7065 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0137. Min Act: -0.0004

Data Index: 105730 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0137. Min Act: -0.0004

Data Index: 74851 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0124. Min Act: -0.0004

Data Index: 1204266 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0139. Min Act: -0.0004

Data Index: 326471 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0125. Min Act: -0.0004

Data Index: 274607 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0126. Min Act: -0.0004

Data Index: 999063 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0123. Min Act: -0.0004

Data Index: 265389 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0116. Min Act: -0.0004

Data Index: 847395 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0004

Data Index: 503601 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0128. Min Act: -0.0004

Data Index: 729191 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0120. Min Act: -0.0004

Data Index: 1324291 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0125. Min Act: -0.0004

Data Index: 1199196 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0118. Min Act: -0.0004

Data Index: 871582 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0119. Min Act: -0.0004

Data Index: 875871 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0116. Min Act: -0.0004

Data Index: 621599 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0122. Min Act: -0.0004

Data Index: 506976 (C4 (Web Text))

Max Activating Token Index: 915