Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 923 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.9324. Min Act: -0.1700

Data Index: 547870 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.8698. Min Act: -0.1700

Data Index: 1171688 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.9011. Min Act: -0.1700

Data Index: 1013898 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.8698. Min Act: -0.1700

Data Index: 105090 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7447. Min Act: -0.1700

Data Index: 1175275 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.7760. Min Act: -0.1700

Data Index: 909146 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 1103686 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 241764 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6821. Min Act: -0.1700

Data Index: 1190017 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 423448 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 279040 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 844987 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 1307223 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6195. Min Act: -0.1700

Data Index: 759401 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 112057 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6195. Min Act: -0.1700

Data Index: 905506 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6195. Min Act: -0.1700

Data Index: 170566 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.6508. Min Act: -0.1700

Data Index: 288580 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.5882. Min Act: -0.1700

Data Index: 45474 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 3.9324. Min Range: -3.9324

Max Act: 3.5882. Min Act: -0.1700

Data Index: 916097 (C4 (Web Text))

Max Activating Token Index: 783