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

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

Neuron 4352 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.9186. Min Act: -0.0000

Data Index: 499115 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1513544 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1475934 (Python Code)

Max Activating Token Index: 316

Text #3

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1639301 (Python Code)

Max Activating Token Index: 684

Text #4

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7908. Min Act: -0.0000

Data Index: 908665 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1378821 (Python Code)

Max Activating Token Index: 475

Text #6

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1604338 (Python Code)

Max Activating Token Index: 734

Text #7

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7291. Min Act: -0.0000

Data Index: 974442 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1528373 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1566477 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1461513 (Python Code)

Max Activating Token Index: 794

Text #11

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1487266 (Python Code)

Max Activating Token Index: 305

Text #12

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1324430 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1521120 (Python Code)

Max Activating Token Index: 957

Text #14

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1637219 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1559711 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1447758 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6143. Min Act: -0.0000

Data Index: 446182 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1618803 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 0.9186. Min Range: -0.9186

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1613817 (Python Code)

Max Activating Token Index: 57