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

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

Neuron 1810 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: 3.9944. Min Range: -3.9944

Max Act: 3.9944. Min Act: -0.1700

Data Index: 1141404 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.9006. Min Act: -0.1700

Data Index: 21300 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.8694. Min Act: -0.1700

Data Index: 956879 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.8694. Min Act: -0.1700

Data Index: 310565 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.8694. Min Act: -0.1700

Data Index: 277770 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.8068. Min Act: -0.1700

Data Index: 127426 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.7442. Min Act: -0.1700

Data Index: 35612 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.7442. Min Act: -0.1700

Data Index: 1232607 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.7442. Min Act: -0.1700

Data Index: 1280156 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.7129. Min Act: -0.1700

Data Index: 659118 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6816. Min Act: -0.1700

Data Index: 625027 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.7129. Min Act: -0.1700

Data Index: 771457 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1294878 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.7129. Min Act: -0.1700

Data Index: 1129666 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.7129. Min Act: -0.1700

Data Index: 398058 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6503. Min Act: -0.1700

Data Index: 195043 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6816. Min Act: -0.1700

Data Index: 1023334 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6503. Min Act: -0.1700

Data Index: 811317 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6816. Min Act: -0.1700

Data Index: 775160 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 3.9944. Min Range: -3.9944

Max Act: 3.6816. Min Act: -0.1700

Data Index: 745185 (C4 (Web Text))

Max Activating Token Index: 968