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

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

Neuron 1421 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0145. Min Act: -0.0002

Data Index: 1261182 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0185. Min Act: -0.0002

Data Index: 483760 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0151. Min Act: -0.0002

Data Index: 396021 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1176434 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1341198 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1195068 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1253617 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0140. Min Act: -0.0002

Data Index: 1008411 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0153. Min Act: -0.0002

Data Index: 883915 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1208819 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0135. Min Act: -0.0002

Data Index: 981862 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0126. Min Act: -0.0002

Data Index: 865224 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0100. Min Act: -0.0002

Data Index: 693088 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0139. Min Act: -0.0002

Data Index: 1150507 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1527752 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1450709 (Python Code)

Max Activating Token Index: 803

Text #16

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0134. Min Act: -0.0002

Data Index: 610243 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1217904 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0133. Min Act: -0.0002

Data Index: 689896 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0185. Min Range: -0.0185

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1239279 (C4 (Web Text))

Max Activating Token Index: 518