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

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

Neuron 1825 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: 5.5339. Min Range: -5.5339

Max Act: 5.5027. Min Act: -0.1700

Data Index: 204886 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.5339. Min Act: -0.1700

Data Index: 429867 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.3152. Min Act: -0.1700

Data Index: 994009 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.2839. Min Act: -0.1699

Data Index: 942832 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.2839. Min Act: -0.1700

Data Index: 492891 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.1589. Min Act: -0.1700

Data Index: 186690 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.2839. Min Act: -0.1700

Data Index: 277836 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.1589. Min Act: -0.1699

Data Index: 247575 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.2214. Min Act: -0.1700

Data Index: 24960 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.1589. Min Act: -0.1700

Data Index: 600233 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.1589. Min Act: -0.1700

Data Index: 713792 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.0964. Min Act: -0.1700

Data Index: 684910 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.1277. Min Act: -0.1699

Data Index: 637737 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.1589. Min Act: -0.1700

Data Index: 65693 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.0027. Min Act: -0.1700

Data Index: 820833 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.0339. Min Act: -0.1700

Data Index: 727546 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.0027. Min Act: -0.1700

Data Index: 283387 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.0339. Min Act: -0.1700

Data Index: 897949 (C4 (Web Text))

Max Activating Token Index: 875

Text #18

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.0652. Min Act: -0.1700

Data Index: 3640 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 5.5339. Min Range: -5.5339

Max Act: 5.0652. Min Act: -0.1700

Data Index: 246327 (C4 (Web Text))

Max Activating Token Index: 456