Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1907 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0232. Min Act: -0.0003

Data Index: 38185 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0164. Min Act: -0.0003

Data Index: 759007 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0159. Min Act: -0.0003

Data Index: 165771 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0146. Min Act: -0.0003

Data Index: 526706 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0148. Min Act: -0.0003

Data Index: 1265928 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1309747 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1250720 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1034688 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0134. Min Act: -0.0003

Data Index: 933956 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0138. Min Act: -0.0003

Data Index: 577862 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1284487 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0133. Min Act: -0.0002

Data Index: 455155 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1348542 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0132. Min Act: -0.0003

Data Index: 855243 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0125. Min Act: -0.0003

Data Index: 107629 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0126. Min Act: -0.0003

Data Index: 465087 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1298730 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1128709 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0122. Min Act: -0.0003

Data Index: 195107 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 0.0232. Min Range: -0.0232

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1018053 (C4 (Web Text))

Max Activating Token Index: 46