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

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

Neuron 1502 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.6203. Min Act: -0.1700

Data Index: 1178894 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.4016. Min Act: -0.1700

Data Index: 1287796 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.3391. Min Act: -0.1700

Data Index: 477715 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.2453. Min Act: -0.1700

Data Index: 1100027 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1828. Min Act: -0.1700

Data Index: 162160 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.3078. Min Act: -0.1700

Data Index: 293308 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.2453. Min Act: -0.1700

Data Index: 336232 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.2141. Min Act: -0.1700

Data Index: 139855 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.2141. Min Act: -0.1700

Data Index: 271526 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.2141. Min Act: -0.1700

Data Index: 827984 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.2141. Min Act: -0.1700

Data Index: 436844 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1828. Min Act: -0.1700

Data Index: 274357 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.2453. Min Act: -0.1700

Data Index: 173756 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1828. Min Act: -0.1700

Data Index: 1239353 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1516. Min Act: -0.1700

Data Index: 417647 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1516. Min Act: -0.1700

Data Index: 1279461 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1203. Min Act: -0.1700

Data Index: 60480 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1203. Min Act: -0.1700

Data Index: 565052 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.1516. Min Act: -0.1700

Data Index: 747390 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 5.6203. Min Range: -5.6203

Max Act: 5.0891. Min Act: -0.1700

Data Index: 1079233 (C4 (Web Text))

Max Activating Token Index: 22