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

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

Neuron 3765 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1430023 (Python Code)

Max Activating Token Index: 263

Text #1

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0067. Min Act: -0.0003

Data Index: 465208 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1609689 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1534015 (Python Code)

Max Activating Token Index: 450

Text #4

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0061. Min Act: -0.0003

Data Index: 421753 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1592559 (Python Code)

Max Activating Token Index: 910

Text #6

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1565086 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1492176 (Python Code)

Max Activating Token Index: 475

Text #8

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 603711 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1376750 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1586981 (Python Code)

Max Activating Token Index: 795

Text #11

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1489433 (Python Code)

Max Activating Token Index: 356

Text #12

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0060. Min Act: -0.0002

Data Index: 1565097 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1361772 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1556943 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0002

Data Index: 1512218 (Python Code)

Max Activating Token Index: 871

Text #16

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0057. Min Act: -0.0002

Data Index: 1443748 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1519795 (Python Code)

Max Activating Token Index: 35

Text #18

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1149097 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0067. Min Range: -0.0067

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1417363 (Python Code)

Max Activating Token Index: 465