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

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

Neuron 504 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2783. Min Range: -5.2783

Max Act: 5.2783. Min Act: -0.1700

Data Index: 485225 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.7783. Min Act: -0.1700

Data Index: 777387 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.8096. Min Act: -0.1700

Data Index: 549378 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.6533. Min Act: -0.1700

Data Index: 218221 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.4502. Min Act: -0.1700

Data Index: 381366 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.3877. Min Act: -0.1700

Data Index: 1067520 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.3877. Min Act: -0.1700

Data Index: 1101505 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.4033. Min Act: -0.1700

Data Index: 359593 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2783. Min Act: -0.1700

Data Index: 1229994 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2939. Min Act: -0.1700

Data Index: 1190533 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.3252. Min Act: -0.1700

Data Index: 1049791 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2939. Min Act: -0.1700

Data Index: 199360 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.3095. Min Act: -0.1700

Data Index: 974935 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2783. Min Act: -0.1700

Data Index: 539610 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2783. Min Act: -0.1700

Data Index: 1087367 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2626. Min Act: -0.1700

Data Index: 595062 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2626. Min Act: -0.1699

Data Index: 1252617 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2783. Min Act: -0.1700

Data Index: 261887 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2783. Min Act: -0.1700

Data Index: 331388 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 5.2783. Min Range: -5.2783

Max Act: 4.2470. Min Act: -0.1700

Data Index: 329185 (C4 (Web Text))

Max Activating Token Index: 218