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

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

Neuron 948 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.1065. Min Act: -0.1700

Data Index: 221970 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0907. Min Act: -0.1700

Data Index: 558603 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0750. Min Act: -0.1700

Data Index: 777767 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0592. Min Act: -0.1700

Data Index: 5956 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0592. Min Act: -0.1700

Data Index: 362034 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0592. Min Act: -0.1700

Data Index: 140484 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0592. Min Act: -0.1700

Data Index: 332865 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0434. Min Act: -0.1700

Data Index: 1074491 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0434. Min Act: -0.1700

Data Index: 1244244 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0592. Min Act: -0.1700

Data Index: 225065 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0276. Min Act: -0.1700

Data Index: 981773 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0276. Min Act: -0.1700

Data Index: 68776 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0434. Min Act: -0.1700

Data Index: 433371 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0276. Min Act: -0.1700

Data Index: 776022 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0434. Min Act: -0.1700

Data Index: 549239 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0276. Min Act: -0.1700

Data Index: 147586 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0118. Min Act: -0.1700

Data Index: 762883 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0434. Min Act: -0.1700

Data Index: 1062791 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0118. Min Act: -0.1700

Data Index: 786598 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 3.1065. Min Range: -3.1065

Max Act: 3.0118. Min Act: -0.1700

Data Index: 909155 (C4 (Web Text))

Max Activating Token Index: 860