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

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

Neuron 556 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.7306. Min Act: -0.1700

Data Index: 54877 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.7619. Min Act: -0.1700

Data Index: 16608 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.6994. Min Act: -0.1700

Data Index: 970961 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.6681. Min Act: -0.1700

Data Index: 257844 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.6994. Min Act: -0.1700

Data Index: 595096 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.2931. Min Act: -0.1700

Data Index: 773181 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.6056. Min Act: -0.1700

Data Index: 114793 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.6056. Min Act: -0.1700

Data Index: 307571 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5744. Min Act: -0.1700

Data Index: 208159 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5119. Min Act: -0.1700

Data Index: 461728 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5119. Min Act: -0.1700

Data Index: 1306223 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5744. Min Act: -0.1700

Data Index: 1080069 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5744. Min Act: -0.1700

Data Index: 1046004 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5119. Min Act: -0.1700

Data Index: 1507245 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5744. Min Act: -0.1700

Data Index: 358891 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.6056. Min Act: -0.1700

Data Index: 513861 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5431. Min Act: -0.1700

Data Index: 205680 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5744. Min Act: -0.1700

Data Index: 369490 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5431. Min Act: -0.1700

Data Index: 709914 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 5.7619. Min Range: -5.7619

Max Act: 5.5431. Min Act: -0.1700

Data Index: 628228 (C4 (Web Text))

Max Activating Token Index: 586