Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1602 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.6462. Min Act: -0.1700

Data Index: 1015476 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.7087. Min Act: -0.1700

Data Index: 871048 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.5837. Min Act: -0.1700

Data Index: 254878 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.3962. Min Act: -0.1700

Data Index: 1279980 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.5212. Min Act: -0.1700

Data Index: 780006 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.3025. Min Act: -0.1700

Data Index: 768903 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.3650. Min Act: -0.1700

Data Index: 1227115 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.3962. Min Act: -0.1700

Data Index: 318589 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.3337. Min Act: -0.1700

Data Index: 1113171 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.3025. Min Act: -0.1700

Data Index: 848841 (C4 (Web Text))

Max Activating Token Index: 542

Text #10

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.3025. Min Act: -0.1700

Data Index: 1053760 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.2712. Min Act: -0.1700

Data Index: 613831 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.2400. Min Act: -0.1700

Data Index: 1304537 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.2712. Min Act: -0.1700

Data Index: 29061 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.2400. Min Act: -0.1700

Data Index: 120541 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.2087. Min Act: -0.1700

Data Index: 56117 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.1775. Min Act: -0.1700

Data Index: 1286027 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.2400. Min Act: -0.1700

Data Index: 564460 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.2087. Min Act: -0.1700

Data Index: 993672 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 7.7087. Min Range: -7.7087

Max Act: 7.1150. Min Act: -0.1700

Data Index: 710087 (C4 (Web Text))

Max Activating Token Index: 906