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

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

Neuron 395 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.3813. Min Act: -0.1700

Data Index: 1299763 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.3813. Min Act: -0.1700

Data Index: 448789 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.3028. Min Act: -0.1700

Data Index: 53966 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.2242. Min Act: -0.1700

Data Index: 617309 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.2242. Min Act: -0.1700

Data Index: 346385 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.1770. Min Act: -0.1700

Data Index: 833957 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.1613. Min Act: -0.1700

Data Index: 110978 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.1298. Min Act: -0.1700

Data Index: 512545 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.1455. Min Act: -0.1700

Data Index: 1149383 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.1455. Min Act: -0.1700

Data Index: 617386 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.1298. Min Act: -0.1700

Data Index: 900925 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0983. Min Act: -0.1700

Data Index: 446889 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0825. Min Act: -0.1700

Data Index: 696296 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0667. Min Act: -0.1700

Data Index: 897264 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0667. Min Act: -0.1700

Data Index: 1311256 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0351. Min Act: -0.1700

Data Index: 53806 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0351. Min Act: -0.1700

Data Index: 695830 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0193. Min Act: -0.1700

Data Index: 476296 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0351. Min Act: -0.1700

Data Index: 355211 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 3.3813. Min Range: -3.3813

Max Act: 3.0193. Min Act: -0.1700

Data Index: 1149159 (C4 (Web Text))

Max Activating Token Index: 105