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

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

Neuron 1815 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: 5.6802. Min Range: -5.6802

Max Act: 5.6489. Min Act: -0.1700

Data Index: 1086293 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.6802. Min Act: -0.1700

Data Index: 248443 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.6802. Min Act: -0.1700

Data Index: 1029457 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5864. Min Act: -0.1700

Data Index: 1243483 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.6489. Min Act: -0.1700

Data Index: 74178 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5864. Min Act: -0.1700

Data Index: 1158149 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.6177. Min Act: -0.1700

Data Index: 994014 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5864. Min Act: -0.1700

Data Index: 1094726 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5552. Min Act: -0.1700

Data Index: 1088061 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.6177. Min Act: -0.1700

Data Index: 841781 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5864. Min Act: -0.1700

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5552. Min Act: -0.1700

Data Index: 795025 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5864. Min Act: -0.1700

Data Index: 1027139 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5239. Min Act: -0.1700

Data Index: 959918 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5864. Min Act: -0.1700

Data Index: 754952 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5552. Min Act: -0.1700

Data Index: 972487 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5552. Min Act: -0.1700

Data Index: 1082459 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5552. Min Act: -0.1700

Data Index: 976146 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5864. Min Act: -0.1700

Data Index: 959924 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 5.6802. Min Range: -5.6802

Max Act: 5.5239. Min Act: -0.1700

Data Index: 560577 (C4 (Web Text))

Max Activating Token Index: 920