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

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

Neuron 207 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.4245. Min Act: -0.1700

Data Index: 411740 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.4089. Min Act: -0.1700

Data Index: 978229 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3932. Min Act: -0.1700

Data Index: 696328 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3618. Min Act: -0.1700

Data Index: 535868 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3618. Min Act: -0.1700

Data Index: 344226 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3618. Min Act: -0.1700

Data Index: 1156199 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3461. Min Act: -0.1700

Data Index: 1238726 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3304. Min Act: -0.1700

Data Index: 558079 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3304. Min Act: -0.1700

Data Index: 690751 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.3147. Min Act: -0.1700

Data Index: 689785 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2990. Min Act: -0.1700

Data Index: 21891 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2990. Min Act: -0.1700

Data Index: 875690 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2990. Min Act: -0.1700

Data Index: 1001166 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2833. Min Act: -0.1700

Data Index: 258378 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2833. Min Act: -0.1700

Data Index: 1220676 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2833. Min Act: -0.1700

Data Index: 887865 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2833. Min Act: -0.1700

Data Index: 1103857 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2833. Min Act: -0.1700

Data Index: 586852 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2676. Min Act: -0.1700

Data Index: 138662 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 3.4245. Min Range: -3.4245

Max Act: 3.2519. Min Act: -0.1700

Data Index: 938264 (C4 (Web Text))

Max Activating Token Index: 921