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

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

Neuron 453 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.1902. Min Act: -0.1700

Data Index: 806621 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.2839. Min Act: -0.1700

Data Index: 149515 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.2214. Min Act: -0.1700

Data Index: 807551 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0964. Min Act: -0.1700

Data Index: 151427 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.1277. Min Act: -0.1700

Data Index: 212505 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0964. Min Act: -0.1700

Data Index: 807601 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0964. Min Act: -0.1700

Data Index: 1226577 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0964. Min Act: -0.1700

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0651. Min Act: -0.1700

Data Index: 132545 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0651. Min Act: -0.1700

Data Index: 33833 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0339. Min Act: -0.1700

Data Index: 884087 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0339. Min Act: -0.1700

Data Index: 571351 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 5.2839. Min Range: -5.2839

Max Act: 4.9401. Min Act: -0.1700

Data Index: 345132 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0026. Min Act: -0.1700

Data Index: 423539 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0026. Min Act: -0.1700

Data Index: 889116 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 5.2839. Min Range: -5.2839

Max Act: 4.9714. Min Act: -0.1700

Data Index: 455310 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0026. Min Act: -0.1700

Data Index: 692054 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0026. Min Act: -0.1700

Data Index: 562641 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 5.2839. Min Range: -5.2839

Max Act: 5.0026. Min Act: -0.1700

Data Index: 482860 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 5.2839. Min Range: -5.2839

Max Act: 4.9714. Min Act: -0.1700

Data Index: 964475 (C4 (Web Text))

Max Activating Token Index: 565