Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 794 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.5369. Min Act: -0.1700

Data Index: 626267 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.4119. Min Act: -0.1700

Data Index: 276744 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.3494. Min Act: -0.1699

Data Index: 973676 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.2869. Min Act: -0.1700

Data Index: 48091 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.2869. Min Act: -0.1700

Data Index: 1320266 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.2869. Min Act: -0.1700

Data Index: 191808 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.2244. Min Act: -0.1699

Data Index: 885708 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.1619. Min Act: -0.1696

Data Index: 953143 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.1619. Min Act: -0.1700

Data Index: 1150535 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0369. Min Act: -0.1699

Data Index: 321888 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0994. Min Act: -0.1700

Data Index: 780631 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0994. Min Act: -0.1700

Data Index: 754584 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0994. Min Act: -0.1699

Data Index: 5653 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0994. Min Act: -0.1700

Data Index: 688454 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0369. Min Act: -0.1700

Data Index: 48842 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0994. Min Act: -0.1700

Data Index: 337428 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0369. Min Act: -0.1700

Data Index: 349566 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0994. Min Act: -0.1700

Data Index: 1220745 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0369. Min Act: -0.1699

Data Index: 441624 (C4 (Web Text))

Max Activating Token Index: 702

Text #19

Max Range: 7.5369. Min Range: -7.5369

Max Act: 7.0994. Min Act: -0.1700

Data Index: 779821 (C4 (Web Text))

Max Activating Token Index: 212