Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1530 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0001

Data Index: 182184 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1243215 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0162. Min Act: -0.0001

Data Index: 1172079 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1014461 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0161. Min Act: -0.0001

Data Index: 562449 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0149. Min Act: -0.0001

Data Index: 882039 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0155. Min Act: -0.0001

Data Index: 937004 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0144. Min Act: -0.0001

Data Index: 742020 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0131. Min Act: -0.0001

Data Index: 685231 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0127. Min Act: -0.0001

Data Index: 522381 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0135. Min Act: -0.0001

Data Index: 1308300 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0139. Min Act: -0.0001

Data Index: 314276 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0142. Min Act: -0.0001

Data Index: 46016 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0132. Min Act: -0.0001

Data Index: 158361 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0134. Min Act: -0.0001

Data Index: 971604 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0121. Min Act: -0.0001

Data Index: 713267 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0120. Min Act: -0.0001

Data Index: 466619 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0129. Min Act: -0.0001

Data Index: 425645 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0125. Min Act: -0.0001

Data Index: 58012 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0127. Min Act: -0.0001

Data Index: 652107 (C4 (Web Text))

Max Activating Token Index: 298