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

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

Neuron 663 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: 5.3063. Min Range: -5.3063

Max Act: 5.3063. Min Act: -0.1700

Data Index: 60733 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.2125. Min Act: -0.1700

Data Index: 581650 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.1188. Min Act: -0.1700

Data Index: 246796 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.1500. Min Act: -0.1700

Data Index: 31737 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0563. Min Act: -0.1700

Data Index: 948170 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0563. Min Act: -0.1700

Data Index: 715132 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0875. Min Act: -0.1700

Data Index: 890616 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0875. Min Act: -0.1700

Data Index: 841766 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0563. Min Act: -0.1700

Data Index: 588972 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0250. Min Act: -0.1700

Data Index: 1136456 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0563. Min Act: -0.1700

Data Index: 1019488 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0563. Min Act: -0.1700

Data Index: 525657 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0563. Min Act: -0.1700

Data Index: 915019 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0563. Min Act: -0.1700

Data Index: 637661 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0250. Min Act: -0.1700

Data Index: 817387 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0250. Min Act: -0.1700

Data Index: 225571 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0250. Min Act: -0.1700

Data Index: 275502 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 5.3063. Min Range: -5.3063

Max Act: 5.0250. Min Act: -0.1700

Data Index: 408532 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 5.3063. Min Range: -5.3063

Max Act: 4.9938. Min Act: -0.1700

Data Index: 905531 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 5.3063. Min Range: -5.3063

Max Act: 4.9938. Min Act: -0.1700

Data Index: 756996 (C4 (Web Text))

Max Activating Token Index: 853