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

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

Neuron 1865 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: 5.8677. Min Range: -5.8677

Max Act: 5.8677. Min Act: -0.1700

Data Index: 946834 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.7739. Min Act: -0.1700

Data Index: 969101 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.7114. Min Act: -0.1700

Data Index: 225202 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.7114. Min Act: -0.1700

Data Index: 607686 (C4 (Web Text))

Max Activating Token Index: 726

Text #4

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.6802. Min Act: -0.1700

Data Index: 198992 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.5864. Min Act: -0.1700

Data Index: 459849 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.5864. Min Act: -0.1700

Data Index: 433732 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.5864. Min Act: -0.1700

Data Index: 563522 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.5864. Min Act: -0.1700

Data Index: 1042044 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.5239. Min Act: -0.1700

Data Index: 791386 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4927. Min Act: -0.1700

Data Index: 897436 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4927. Min Act: -0.1700

Data Index: 553098 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4614. Min Act: -0.1700

Data Index: 580526 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4614. Min Act: -0.1700

Data Index: 870096 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4302. Min Act: -0.1700

Data Index: 592646 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4927. Min Act: -0.1700

Data Index: 885155 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4927. Min Act: -0.1700

Data Index: 500679 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.4302. Min Act: -0.1700

Data Index: 936406 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.3677. Min Act: -0.1700

Data Index: 266061 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 5.8677. Min Range: -5.8677

Max Act: 5.3989. Min Act: -0.1700

Data Index: 1110982 (C4 (Web Text))

Max Activating Token Index: 209