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

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

Neuron 80 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: 3.9577. Min Range: -3.9577

Max Act: 3.9577. Min Act: -0.1700

Data Index: 1068063 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1700

Data Index: 283066 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1699

Data Index: 519400 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.9264. Min Act: -0.1700

Data Index: 540622 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.9264. Min Act: -0.1700

Data Index: 118746 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.9264. Min Act: -0.1700

Data Index: 630103 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1700

Data Index: 506048 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1700

Data Index: 266313 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1042224 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8639. Min Act: -0.1700

Data Index: 645215 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8639. Min Act: -0.1700

Data Index: 1281486 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8639. Min Act: -0.1700

Data Index: 442400 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1700

Data Index: 627231 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1293904 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1699

Data Index: 278205 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1699

Data Index: 280831 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8326. Min Act: -0.1700

Data Index: 248455 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8326. Min Act: -0.1700

Data Index: 827790 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8951. Min Act: -0.1700

Data Index: 45886 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 3.9577. Min Range: -3.9577

Max Act: 3.8639. Min Act: -0.1700

Data Index: 1068760 (C4 (Web Text))

Max Activating Token Index: 766