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

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

Neuron 991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1849. Min Range: -5.1849

Max Act: 5.1849. Min Act: -0.1700

Data Index: 712865 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 5.1849. Min Range: -5.1849

Max Act: 5.1849. Min Act: -0.1700

Data Index: 31407 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 5.1849. Min Range: -5.1849

Max Act: 5.1849. Min Act: -0.1700

Data Index: 1261557 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 5.1849. Min Range: -5.1849

Max Act: 5.0286. Min Act: -0.1700

Data Index: 38537 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 5.1849. Min Range: -5.1849

Max Act: 5.0599. Min Act: -0.1700

Data Index: 1043854 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 5.1849. Min Range: -5.1849

Max Act: 5.0911. Min Act: -0.1700

Data Index: 921066 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 5.1849. Min Range: -5.1849

Max Act: 5.0911. Min Act: -0.1700

Data Index: 1082270 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.9974. Min Act: -0.1700

Data Index: 1058671 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.9349. Min Act: -0.1700

Data Index: 454700 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.8411. Min Act: -0.1700

Data Index: 632028 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.9036. Min Act: -0.1700

Data Index: 190220 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.9036. Min Act: -0.1700

Data Index: 467735 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.7786. Min Act: -0.1700

Data Index: 32970 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.8099. Min Act: -0.1700

Data Index: 261214 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.9036. Min Act: -0.1700

Data Index: 106283 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.8411. Min Act: -0.1700

Data Index: 466808 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.8411. Min Act: -0.1700

Data Index: 351455 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.7474. Min Act: -0.1700

Data Index: 869583 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.8099. Min Act: -0.1700

Data Index: 1296645 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 5.1849. Min Range: -5.1849

Max Act: 4.8411. Min Act: -0.1700

Data Index: 1328495 (C4 (Web Text))

Max Activating Token Index: 660