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

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

Neuron 325 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: 0.0217. Min Range: -0.0217

Max Act: 0.0217. Min Act: -0.0005

Data Index: 417182 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0191. Min Act: -0.0005

Data Index: 779547 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0167. Min Act: -0.0006

Data Index: 905311 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1100001 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0155. Min Act: -0.0006

Data Index: 821580 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0154. Min Act: -0.0006

Data Index: 659339 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0149. Min Act: -0.0005

Data Index: 1105995 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0147. Min Act: -0.0006

Data Index: 105809 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0141. Min Act: -0.0006

Data Index: 814986 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0135. Min Act: -0.0005

Data Index: 255869 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0133. Min Act: -0.0006

Data Index: 807613 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0131. Min Act: -0.0006

Data Index: 452309 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0128. Min Act: -0.0005

Data Index: 178863 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0126. Min Act: -0.0006

Data Index: 217766 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1359807 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0124. Min Act: -0.0006

Data Index: 300968 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0124. Min Act: -0.0006

Data Index: 1166733 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0120. Min Act: -0.0006

Data Index: 629519 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0119. Min Act: -0.0006

Data Index: 1123671 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0217. Min Range: -0.0217

Max Act: 0.0121. Min Act: -0.0006

Data Index: 810226 (C4 (Web Text))

Max Activating Token Index: 740