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

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

Neuron 3209 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: 0.8470. Min Range: -0.8470

Max Act: 0.8470. Min Act: -0.0002

Data Index: 1562751 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7167. Min Act: -0.0002

Data Index: 1463984 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6605. Min Act: -0.0002

Data Index: 1644131 (Python Code)

Max Activating Token Index: 936

Text #3

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7067. Min Act: -0.0002

Data Index: 1418454 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.8030. Min Act: -0.0002

Data Index: 1545947 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6429. Min Act: -0.0002

Data Index: 1600713 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7053. Min Act: -0.0002

Data Index: 1398433 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6313. Min Act: -0.0002

Data Index: 1546060 (Python Code)

Max Activating Token Index: 998

Text #8

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7213. Min Act: -0.0002

Data Index: 1530622 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5045. Min Act: -0.0002

Data Index: 1656264 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7310. Min Act: -0.0002

Data Index: 1506001 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6422. Min Act: -0.0002

Data Index: 1644299 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5732. Min Act: -0.0002

Data Index: 1623606 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6172. Min Act: -0.0002

Data Index: 1634568 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.5935. Min Act: -0.0002

Data Index: 1504654 (Python Code)

Max Activating Token Index: 951

Text #15

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6402. Min Act: -0.0002

Data Index: 1537895 (Python Code)

Max Activating Token Index: 977

Text #16

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6105. Min Act: -0.0002

Data Index: 1446764 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6140. Min Act: -0.0002

Data Index: 1469821 (Python Code)

Max Activating Token Index: 754

Text #18

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.6872. Min Act: -0.0002

Data Index: 1473599 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.8470. Min Range: -0.8470

Max Act: 0.7032. Min Act: -0.0002

Data Index: 1418861 (Python Code)

Max Activating Token Index: 1021