Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1930 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0006

Data Index: 705600 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1135951 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0006

Data Index: 80858 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0150. Min Act: -0.0006

Data Index: 192340 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0148. Min Act: -0.0006

Data Index: 268059 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0159. Min Act: -0.0006

Data Index: 151525 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0144. Min Act: -0.0006

Data Index: 84718 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0137. Min Act: -0.0006

Data Index: 738080 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0144. Min Act: -0.0006

Data Index: 1067143 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1180114 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0135. Min Act: -0.0006

Data Index: 887573 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0153. Min Act: -0.0006

Data Index: 795037 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0145. Min Act: -0.0006

Data Index: 147427 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0163. Min Act: -0.0006

Data Index: 634046 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0164. Min Act: -0.0006

Data Index: 844024 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0006

Data Index: 466480 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1098233 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0129. Min Act: -0.0006

Data Index: 666798 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0136. Min Act: -0.0006

Data Index: 1162085 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0130. Min Act: -0.0006

Data Index: 44910 (C4 (Web Text))

Max Activating Token Index: 278