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

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

Neuron 982 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: 3.8595. Min Range: -3.8595

Max Act: 3.8595. Min Act: -0.1700

Data Index: 625314 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6717. Min Act: -0.1700

Data Index: 91767 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6404. Min Act: -0.1700

Data Index: 975315 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6091. Min Act: -0.1700

Data Index: 649509 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5465. Min Act: -0.1700

Data Index: 264017 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5465. Min Act: -0.1700

Data Index: 975391 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5778. Min Act: -0.1700

Data Index: 1120172 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.6091. Min Act: -0.1700

Data Index: 989338 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5778. Min Act: -0.1700

Data Index: 434640 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5778. Min Act: -0.1700

Data Index: 561902 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5465. Min Act: -0.1700

Data Index: 1278352 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5778. Min Act: -0.1700

Data Index: 1168469 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.4838. Min Act: -0.1700

Data Index: 952359 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5778. Min Act: -0.1700

Data Index: 1254919 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5778. Min Act: -0.1700

Data Index: 1277977 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5465. Min Act: -0.1700

Data Index: 1218968 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5465. Min Act: -0.1700

Data Index: 557841 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.5152. Min Act: -0.1700

Data Index: 434522 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.4525. Min Act: -0.1700

Data Index: 33136 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 3.8595. Min Range: -3.8595

Max Act: 3.4838. Min Act: -0.1700

Data Index: 850027 (C4 (Web Text))

Max Activating Token Index: 52