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

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

Neuron 256 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: 5.5592. Min Range: -5.5592

Max Act: 5.5592. Min Act: -0.1700

Data Index: 683345 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.4655. Min Act: -0.1700

Data Index: 1074711 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.4030. Min Act: -0.1700

Data Index: 885718 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.4030. Min Act: -0.1700

Data Index: 940804 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.4030. Min Act: -0.1700

Data Index: 1290244 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3717. Min Act: -0.1700

Data Index: 1317745 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3405. Min Act: -0.1700

Data Index: 739735 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3405. Min Act: -0.1700

Data Index: 452179 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3405. Min Act: -0.1700

Data Index: 878668 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3092. Min Act: -0.1700

Data Index: 638328 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3405. Min Act: -0.1700

Data Index: 753322 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.2780. Min Act: -0.1700

Data Index: 967060 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3092. Min Act: -0.1700

Data Index: 904646 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3092. Min Act: -0.1700

Data Index: 671565 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3092. Min Act: -0.1700

Data Index: 776928 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3092. Min Act: -0.1700

Data Index: 1258235 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.2780. Min Act: -0.1700

Data Index: 297098 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.2780. Min Act: -0.1700

Data Index: 1158215 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.2780. Min Act: -0.1700

Data Index: 327955 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 5.5592. Min Range: -5.5592

Max Act: 5.3092. Min Act: -0.1700

Data Index: 2007 (C4 (Web Text))

Max Activating Token Index: 697