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

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

Neuron 0 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: 3.5976. Min Range: -3.5976

Max Act: 3.5976. Min Act: -0.1700

Data Index: 739067 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.5976. Min Act: -0.1700

Data Index: 1253131 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.4409. Min Act: -0.1700

Data Index: 88622 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.4409. Min Act: -0.1700

Data Index: 318614 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.4095. Min Act: -0.1700

Data Index: 1258682 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.3154. Min Act: -0.1700

Data Index: 281346 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.3468. Min Act: -0.1700

Data Index: 834779 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.3782. Min Act: -0.1700

Data Index: 378334 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2840. Min Act: -0.1700

Data Index: 1304158 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.3468. Min Act: -0.1700

Data Index: 476762 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2526. Min Act: -0.1700

Data Index: 539053 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2526. Min Act: -0.1700

Data Index: 1077447 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2211. Min Act: -0.1700

Data Index: 821456 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2526. Min Act: -0.1700

Data Index: 781491 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2526. Min Act: -0.1700

Data Index: 179247 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2211. Min Act: -0.1700

Data Index: 1094462 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.1582. Min Act: -0.1700

Data Index: 871153 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2526. Min Act: -0.1700

Data Index: 746671 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2526. Min Act: -0.1700

Data Index: 707809 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 3.5976. Min Range: -3.5976

Max Act: 3.2526. Min Act: -0.1700

Data Index: 937979 (C4 (Web Text))

Max Activating Token Index: 770