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

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

Neuron 5027 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0230. Min Act: -0.0000

Data Index: 1452861 (Python Code)

Max Activating Token Index: 936

Text #1

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0173. Min Act: -0.0000

Data Index: 4402 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0172. Min Act: -0.0000

Data Index: 1561332 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0166. Min Act: -0.0000

Data Index: 1532694 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0159. Min Act: -0.0000

Data Index: 526593 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0168. Min Act: -0.0000

Data Index: 1591774 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0167. Min Act: -0.0000

Data Index: 1606164 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0151. Min Act: -0.0000

Data Index: 147454 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0146. Min Act: -0.0001

Data Index: 53902 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1499598 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0143. Min Act: -0.0000

Data Index: 824844 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1228424 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0174. Min Act: -0.0000

Data Index: 1518446 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0142. Min Act: -0.0000

Data Index: 39132 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1606505 (Python Code)

Max Activating Token Index: 996

Text #15

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0141. Min Act: -0.0000

Data Index: 1462656 (Python Code)

Max Activating Token Index: 840

Text #16

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0142. Min Act: -0.0000

Data Index: 1432691 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0142. Min Act: -0.0000

Data Index: 98546 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0143. Min Act: -0.0000

Data Index: 285313 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.0230. Min Range: -0.0230

Max Act: 0.0133. Min Act: -0.0000

Data Index: 1362765 (Python Code)

Max Activating Token Index: 1002