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

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

Neuron 395 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0141. Min Act: -0.0002

Data Index: 989513 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0137. Min Act: -0.0002

Data Index: 651455 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0137. Min Act: -0.0002

Data Index: 664730 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1149781 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0002

Data Index: 758692 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0002

Data Index: 751387 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0134. Min Act: -0.0002

Data Index: 384287 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1293573 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0002

Data Index: 100789 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1154930 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0132. Min Act: -0.0002

Data Index: 940301 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0131. Min Act: -0.0002

Data Index: 644486 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0130. Min Act: -0.0002

Data Index: 938879 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0002

Data Index: 595113 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0133. Min Act: -0.0002

Data Index: 824966 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0002

Data Index: 456189 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0002

Data Index: 340415 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1137512 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0127. Min Act: -0.0002

Data Index: 291427 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.0141. Min Range: -0.0141

Max Act: 0.0126. Min Act: -0.0002

Data Index: 615859 (C4 (Web Text))

Max Activating Token Index: 765