Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1868 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1648107 (Python Code)

Max Activating Token Index: 757

Text #1

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0151. Min Act: -0.0006

Data Index: 6418 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0150. Min Act: -0.0006

Data Index: 773116 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1343439 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0142. Min Act: -0.0006

Data Index: 397520 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1036034 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0143. Min Act: -0.0006

Data Index: 842860 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0143. Min Act: -0.0005

Data Index: 1572576 (Python Code)

Max Activating Token Index: 739

Text #8

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0143. Min Act: -0.0006

Data Index: 1207454 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0142. Min Act: -0.0006

Data Index: 1380496 (Python Code)

Max Activating Token Index: 631

Text #10

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0141. Min Act: -0.0005

Data Index: 1656933 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1371336 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1379377 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0138. Min Act: -0.0006

Data Index: 1568630 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0139. Min Act: -0.0007

Data Index: 700552 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0134. Min Act: -0.0006

Data Index: 401324 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0136. Min Act: -0.0006

Data Index: 18195 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0134. Min Act: -0.0006

Data Index: 472005 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0134. Min Act: -0.0006

Data Index: 579161 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0154. Min Range: -0.0154

Max Act: 0.0133. Min Act: -0.0005

Data Index: 79777 (C4 (Web Text))

Max Activating Token Index: 462