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

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

Neuron 1665 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.5903. Min Act: -0.1700

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.5747. Min Act: -0.1700

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.5434. Min Act: -0.1700

Data Index: 1208391 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.2934. Min Act: -0.1699

Data Index: 1040733 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.3247. Min Act: -0.1700

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.2934. Min Act: -0.1700

Data Index: 1243483 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.2622. Min Act: -0.1700

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.2622. Min Act: -0.1700

Data Index: 1237397 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.1840. Min Act: -0.1700

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.1528. Min Act: -0.1700

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.1215. Min Act: -0.1700

Data Index: 288319 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.0747. Min Act: -0.1700

Data Index: 1327693 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.0747. Min Act: -0.1700

Data Index: 841781 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.1528. Min Act: -0.1700

Data Index: 1086293 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.1528. Min Act: -0.1700

Data Index: 205209 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.0278. Min Act: -0.1699

Data Index: 1293781 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.1372. Min Act: -0.1700

Data Index: 295739 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.0590. Min Act: -0.1700

Data Index: 753164 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 5.5903. Min Range: -5.5903

Max Act: 5.0903. Min Act: -0.1700

Data Index: 1351586 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 5.5903. Min Range: -5.5903

Max Act: 4.9965. Min Act: -0.1700

Data Index: 1348858 (C4 (Web Text))

Max Activating Token Index: 611