Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 465 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0004

Data Index: 563607 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0073. Min Act: -0.0004

Data Index: 1523267 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1035902 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0072. Min Act: -0.0004

Data Index: 1193349 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0004

Data Index: 623899 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0004

Data Index: 312097 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1369657 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1581460 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0069. Min Act: -0.0004

Data Index: 705847 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1177378 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1558150 (Python Code)

Max Activating Token Index: 78

Text #11

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1540494 (Python Code)

Max Activating Token Index: 657

Text #12

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1464918 (Python Code)

Max Activating Token Index: 899

Text #13

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1413012 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1001381 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0004

Data Index: 889344 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1546947 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1511319 (Python Code)

Max Activating Token Index: 478

Text #18

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1600540 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 0.0073. Min Range: -0.0073

Max Act: 0.0067. Min Act: -0.0004

Data Index: 923052 (C4 (Web Text))

Max Activating Token Index: 4