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

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

Neuron 1987 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.5820. Min Act: -0.1700

Data Index: 1139638 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.5037. Min Act: -0.1700

Data Index: 363889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.4724. Min Act: -0.1700

Data Index: 1597349 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.4097. Min Act: -0.1700

Data Index: 1353399 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1193076 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 1320859 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3940. Min Act: -0.1700

Data Index: 993099 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 1117340 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3940. Min Act: -0.1700

Data Index: 1274234 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 642523 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 914837 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 282121 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 791334 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 1288085 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3783. Min Act: -0.1700

Data Index: 593686 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3469. Min Act: -0.1700

Data Index: 842803 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3626. Min Act: -0.1700

Data Index: 1138946 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3626. Min Act: -0.1700

Data Index: 534217 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3626. Min Act: -0.1700

Data Index: 1130867 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 3.5820. Min Range: -3.5820

Max Act: 3.3626. Min Act: -0.1700

Data Index: 522151 (C4 (Web Text))

Max Activating Token Index: 911