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

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

Neuron 532 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1918. Min Act: -0.0001

Data Index: 424476 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1994. Min Act: -0.0001

Data Index: 29082 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.2063. Min Act: -0.0001

Data Index: 203604 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1823. Min Act: -0.0001

Data Index: 376083 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1768. Min Act: -0.0001

Data Index: 777669 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1059357 (C4 (Web Text))

Max Activating Token Index: 717

Text #6

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1783. Min Act: -0.0001

Data Index: 726519 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1666. Min Act: -0.0001

Data Index: 852740 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1652. Min Act: -0.0000

Data Index: 448201 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1189145 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1737. Min Act: -0.0001

Data Index: 664565 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1728. Min Act: -0.0001

Data Index: 400177 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1620. Min Act: -0.0000

Data Index: 248810 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1737. Min Act: -0.0001

Data Index: 1286271 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1123045 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1680. Min Act: -0.0001

Data Index: 725613 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1138457 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1358149 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1653. Min Act: -0.0001

Data Index: 119425 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1525. Min Act: -0.0001

Data Index: 144419 (C4 (Web Text))

Max Activating Token Index: 250