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

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

Neuron 383 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.3384. Min Act: -0.1700

Data Index: 744327 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.4322. Min Act: -0.1700

Data Index: 643404 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.4322. Min Act: -0.1700

Data Index: 1222823 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.3384. Min Act: -0.1700

Data Index: 1339841 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2759. Min Act: -0.1700

Data Index: 851900 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.3697. Min Act: -0.1700

Data Index: 456749 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.3697. Min Act: -0.1700

Data Index: 73289 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.3072. Min Act: -0.1700

Data Index: 945306 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.3072. Min Act: -0.1700

Data Index: 557469 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2134. Min Act: -0.1700

Data Index: 979241 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.4009. Min Act: -0.1700

Data Index: 339180 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2759. Min Act: -0.1700

Data Index: 764117 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2134. Min Act: -0.1700

Data Index: 592502 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.1822. Min Act: -0.1700

Data Index: 1153175 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2447. Min Act: -0.1700

Data Index: 336910 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2134. Min Act: -0.1700

Data Index: 544102 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 6.4322. Min Range: -6.4322

Max Act: 5.9947. Min Act: -0.1700

Data Index: 1132597 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2447. Min Act: -0.1700

Data Index: 163048 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.2134. Min Act: -0.1700

Data Index: 801566 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 6.4322. Min Range: -6.4322

Max Act: 6.1509. Min Act: -0.1700

Data Index: 692342 (C4 (Web Text))

Max Activating Token Index: 564