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

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

Neuron 1122 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5622. Min Act: -0.0000

Data Index: 1559412 (Python Code)

Max Activating Token Index: 213

Text #1

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5735. Min Act: -0.0000

Data Index: 1386069 (Python Code)

Max Activating Token Index: 187

Text #2

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.8152. Min Act: -0.0000

Data Index: 1650835 (Python Code)

Max Activating Token Index: 297

Text #3

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.7857. Min Act: -0.0000

Data Index: 1533732 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5681. Min Act: -0.0000

Data Index: 1462658 (Python Code)

Max Activating Token Index: 224

Text #5

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6443. Min Act: -0.0000

Data Index: 1622713 (Python Code)

Max Activating Token Index: 67

Text #6

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4432. Min Act: -0.0000

Data Index: 1360992 (Python Code)

Max Activating Token Index: 270

Text #7

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5932. Min Act: -0.0000

Data Index: 1578466 (Python Code)

Max Activating Token Index: 325

Text #8

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1602071 (Python Code)

Max Activating Token Index: 475

Text #9

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1540714 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.5494. Min Act: -0.0000

Data Index: 1527870 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1513413 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4519. Min Act: -0.0000

Data Index: 1508397 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1588448 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1597823 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1440726 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1428621 (Python Code)

Max Activating Token Index: 71

Text #17

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.4017. Min Act: -0.0000

Data Index: 1478041 (Python Code)

Max Activating Token Index: 433

Text #18

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.3814. Min Act: -0.0000

Data Index: 1455204 (Python Code)

Max Activating Token Index: 330

Text #19

Max Range: 1.8152. Min Range: -1.8152

Max Act: 1.6864. Min Act: -0.0000

Data Index: 1360001 (Python Code)

Max Activating Token Index: 215