Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 851 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3680. Min Act: -0.1700

Data Index: 86559 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3992. Min Act: -0.1700

Data Index: 627441 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3992. Min Act: -0.1700

Data Index: 1052364 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3055. Min Act: -0.1700

Data Index: 268330 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3055. Min Act: -0.1699

Data Index: 188892 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.3055. Min Act: -0.1700

Data Index: 1186987 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2742. Min Act: -0.1700

Data Index: 825004 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2117. Min Act: -0.1699

Data Index: 694269 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2742. Min Act: -0.1700

Data Index: 999428 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2430. Min Act: -0.1700

Data Index: 808432 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2430. Min Act: -0.1700

Data Index: 1112522 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2430. Min Act: -0.1700

Data Index: 865342 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2117. Min Act: -0.1700

Data Index: 589328 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.1805. Min Act: -0.1700

Data Index: 347847 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.1805. Min Act: -0.1700

Data Index: 943528 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2430. Min Act: -0.1700

Data Index: 399777 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2117. Min Act: -0.1700

Data Index: 728102 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2117. Min Act: -0.1700

Data Index: 1143810 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.2117. Min Act: -0.1699

Data Index: 91658 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 5.3992. Min Range: -5.3992

Max Act: 5.1805. Min Act: -0.1700

Data Index: 1176041 (C4 (Web Text))

Max Activating Token Index: 188