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

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

Neuron 1441 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4954. Min Act: -0.1700

Data Index: 1526628 (Python Code)

Max Activating Token Index: 869

Text #1

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4797. Min Act: -0.1700

Data Index: 1651940 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4484. Min Act: -0.1700

Data Index: 1348467 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4327. Min Act: -0.1700

Data Index: 854867 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3700. Min Act: -0.1700

Data Index: 1028667 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4170. Min Act: -0.1700

Data Index: 376266 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4170. Min Act: -0.1700

Data Index: 362095 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4013. Min Act: -0.1700

Data Index: 1358973 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3856. Min Act: -0.1700

Data Index: 911330 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.2600. Min Act: -0.1700

Data Index: 367015 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3856. Min Act: -0.1700

Data Index: 343747 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3856. Min Act: -0.1700

Data Index: 760343 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.4013. Min Act: -0.1700

Data Index: 764041 (C4 (Web Text))

Max Activating Token Index: 253

Text #13

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3543. Min Act: -0.1700

Data Index: 985277 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3700. Min Act: -0.1700

Data Index: 1274954 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3700. Min Act: -0.1700

Data Index: 1209192 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3700. Min Act: -0.1700

Data Index: 234954 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3386. Min Act: -0.1700

Data Index: 529882 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3072. Min Act: -0.1700

Data Index: 384417 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 3.4954. Min Range: -3.4954

Max Act: 3.3543. Min Act: -0.1700

Data Index: 277793 (C4 (Web Text))

Max Activating Token Index: 957