Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1109 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1730. Min Act: -0.1700

Data Index: 82926 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1730. Min Act: -0.1700

Data Index: 1094250 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1730. Min Act: -0.1700

Data Index: 1014106 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1573. Min Act: -0.1700

Data Index: 342300 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1100. Min Act: -0.1700

Data Index: 1070681 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1100. Min Act: -0.1700

Data Index: 681782 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1100. Min Act: -0.1700

Data Index: 293900 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1258. Min Act: -0.1700

Data Index: 518788 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.1100. Min Act: -0.1700

Data Index: 949871 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0943. Min Act: -0.1700

Data Index: 1141447 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0785. Min Act: -0.1700

Data Index: 827209 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0627. Min Act: -0.1700

Data Index: 755826 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0785. Min Act: -0.1700

Data Index: 1012093 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0627. Min Act: -0.1700

Data Index: 981900 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0785. Min Act: -0.1700

Data Index: 1282579 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0627. Min Act: -0.1700

Data Index: 1136144 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0311. Min Act: -0.1700

Data Index: 609809 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1091593 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0627. Min Act: -0.1700

Data Index: 595930 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 3.1730. Min Range: -3.1730

Max Act: 3.0469. Min Act: -0.1700

Data Index: 1125001 (C4 (Web Text))

Max Activating Token Index: 324