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

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

Neuron 1772 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1505. Min Range: -7.1505

Max Act: 7.1505. Min Act: -0.1700

Data Index: 1248622 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.6817. Min Act: -0.1700

Data Index: 2815 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.5567. Min Act: -0.1700

Data Index: 737475 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.4005. Min Act: -0.1700

Data Index: 351436 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.4630. Min Act: -0.1700

Data Index: 82331 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.4005. Min Act: -0.1699

Data Index: 274473 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.3380. Min Act: -0.1700

Data Index: 1358401 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2442. Min Act: -0.1700

Data Index: 508385 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.3380. Min Act: -0.1700

Data Index: 965769 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2755. Min Act: -0.1700

Data Index: 230193 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.3067. Min Act: -0.1700

Data Index: 758989 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.3067. Min Act: -0.1700

Data Index: 501711 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2755. Min Act: -0.1700

Data Index: 232367 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.3067. Min Act: -0.1700

Data Index: 870336 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2442. Min Act: -0.1700

Data Index: 991061 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2755. Min Act: -0.1700

Data Index: 1006955 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.1817. Min Act: -0.1700

Data Index: 332896 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2442. Min Act: -0.1700

Data Index: 557347 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2755. Min Act: -0.1700

Data Index: 329745 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 7.1505. Min Range: -7.1505

Max Act: 6.2755. Min Act: -0.1700

Data Index: 1061496 (C4 (Web Text))

Max Activating Token Index: 861