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

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

Neuron 1649 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: 3.6858. Min Range: -3.6858

Max Act: 3.6858. Min Act: -0.1700

Data Index: 691139 (C4 (Web Text))

Max Activating Token Index: 183

Text #1

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.6858. Min Act: -0.1700

Data Index: 882472 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5919. Min Act: -0.1700

Data Index: 836026 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5919. Min Act: -0.1700

Data Index: 908178 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5919. Min Act: -0.1700

Data Index: 611425 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5919. Min Act: -0.1700

Data Index: 1088649 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5293. Min Act: -0.1700

Data Index: 1260767 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5919. Min Act: -0.1700

Data Index: 1288424 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5919. Min Act: -0.1700

Data Index: 206916 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5606. Min Act: -0.1700

Data Index: 342031 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5606. Min Act: -0.1700

Data Index: 1310197 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5293. Min Act: -0.1700

Data Index: 695786 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.4666. Min Act: -0.1700

Data Index: 740674 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5293. Min Act: -0.1700

Data Index: 1300159 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5293. Min Act: -0.1700

Data Index: 522643 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.4666. Min Act: -0.1700

Data Index: 450414 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5293. Min Act: -0.1700

Data Index: 715954 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.5293. Min Act: -0.1700

Data Index: 322403 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.4666. Min Act: -0.1700

Data Index: 276119 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 3.6858. Min Range: -3.6858

Max Act: 3.4979. Min Act: -0.1700

Data Index: 45200 (C4 (Web Text))

Max Activating Token Index: 782