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

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

Neuron 3845 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.3188. Min Act: -0.0002

Data Index: 1653276 (Python Code)

Max Activating Token Index: 230

Text #1

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1978. Min Act: -0.0002

Data Index: 1443375 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.2079. Min Act: -0.0002

Data Index: 1556520 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9957. Min Act: -0.0002

Data Index: 1539103 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.2671. Min Act: -0.0002

Data Index: 1627097 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.2158. Min Act: -0.0002

Data Index: 1419649 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1689. Min Act: -0.0002

Data Index: 1364823 (Python Code)

Max Activating Token Index: 1004

Text #7

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1830. Min Act: -0.0002

Data Index: 1639062 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1682. Min Act: -0.0002

Data Index: 1573075 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1477. Min Act: -0.0002

Data Index: 1475827 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1331. Min Act: -0.0002

Data Index: 1368646 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1861. Min Act: -0.0002

Data Index: 1525739 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0872. Min Act: -0.0002

Data Index: 1438015 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0848. Min Act: -0.0002

Data Index: 1539814 (Python Code)

Max Activating Token Index: 321

Text #14

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0894. Min Act: -0.0002

Data Index: 1513465 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.3093. Min Act: -0.0002

Data Index: 1396983 (Python Code)

Max Activating Token Index: 141

Text #16

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1100. Min Act: -0.0002

Data Index: 1403640 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1068. Min Act: -0.0002

Data Index: 1499191 (Python Code)

Max Activating Token Index: 525

Text #18

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9741. Min Act: -0.0002

Data Index: 1375745 (Python Code)

Max Activating Token Index: 73

Text #19

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0140. Min Act: -0.0002

Data Index: 1499147 (Python Code)

Max Activating Token Index: 116