Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1699 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.1467. Min Act: -0.1700

Data Index: 705540 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0994. Min Act: -0.1700

Data Index: 816295 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0836. Min Act: -0.1700

Data Index: 401631 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0994. Min Act: -0.1700

Data Index: 294207 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0521. Min Act: -0.1700

Data Index: 676960 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0521. Min Act: -0.1700

Data Index: 1174807 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0363. Min Act: -0.1700

Data Index: 660295 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0363. Min Act: -0.1700

Data Index: 497513 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0363. Min Act: -0.1700

Data Index: 340672 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0363. Min Act: -0.1700

Data Index: 1228699 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0363. Min Act: -0.1700

Data Index: 418786 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0047. Min Act: -0.1700

Data Index: 1102048 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 3.1467. Min Range: -3.1467

Max Act: 2.9889. Min Act: -0.1700

Data Index: 1342994 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 3.1467. Min Range: -3.1467

Max Act: 2.9889. Min Act: -0.1700

Data Index: 1205968 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 3.1467. Min Range: -3.1467

Max Act: 2.9889. Min Act: -0.1700

Data Index: 1241847 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.1467. Min Range: -3.1467

Max Act: 2.9889. Min Act: -0.1700

Data Index: 931439 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 3.1467. Min Range: -3.1467

Max Act: 2.9730. Min Act: -0.1700

Data Index: 847260 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 3.1467. Min Range: -3.1467

Max Act: 2.9730. Min Act: -0.1700

Data Index: 81416 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 3.1467. Min Range: -3.1467

Max Act: 3.0047. Min Act: -0.1700

Data Index: 518612 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 3.1467. Min Range: -3.1467

Max Act: 2.9730. Min Act: -0.1700

Data Index: 979631 (C4 (Web Text))

Max Activating Token Index: 54