Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3489 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1180116 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1239. Min Act: -0.0000

Data Index: 1259348 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1467908 (Python Code)

Max Activating Token Index: 355

Text #3

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1196. Min Act: -0.0001

Data Index: 968572 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1118. Min Act: -0.0001

Data Index: 14939 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1206. Min Act: -0.0000

Data Index: 90518 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1195308 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1285232 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1431810 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1023. Min Act: -0.0001

Data Index: 739382 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1091. Min Act: -0.0001

Data Index: 970551 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1639999 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0949. Min Act: -0.0001

Data Index: 160096 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1098. Min Act: -0.0000

Data Index: 873064 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0997. Min Act: -0.0000

Data Index: 739469 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1152259 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0989. Min Act: -0.0001

Data Index: 608358 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1113. Min Act: -0.0001

Data Index: 31298 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1475753 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0975. Min Act: -0.0001

Data Index: 1039098 (C4 (Web Text))

Max Activating Token Index: 593