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

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

Neuron 124 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: 5.9023. Min Range: -5.9023

Max Act: 5.9023. Min Act: -0.1700

Data Index: 1337925 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.9023. Min Act: -0.1700

Data Index: 867037 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.8711. Min Act: -0.1699

Data Index: 76036 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.8398. Min Act: -0.1700

Data Index: 859077 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.8086. Min Act: -0.1700

Data Index: 547685 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.8086. Min Act: -0.1700

Data Index: 642269 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.7461. Min Act: -0.1700

Data Index: 12116 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.7773. Min Act: -0.1700

Data Index: 635905 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.7148. Min Act: -0.1700

Data Index: 586327 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.7461. Min Act: -0.1700

Data Index: 838938 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.7461. Min Act: -0.1700

Data Index: 326046 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.7461. Min Act: -0.1700

Data Index: 1203244 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6836. Min Act: -0.1700

Data Index: 1321869 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6523. Min Act: -0.1700

Data Index: 1199115 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6836. Min Act: -0.1700

Data Index: 285978 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6836. Min Act: -0.1700

Data Index: 977285 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6836. Min Act: -0.1700

Data Index: 150266 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6523. Min Act: -0.1700

Data Index: 456358 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6211. Min Act: -0.1700

Data Index: 1028216 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 5.9023. Min Range: -5.9023

Max Act: 5.6523. Min Act: -0.1700

Data Index: 1096568 (C4 (Web Text))

Max Activating Token Index: 993