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

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

Neuron 1264 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: 3.8324. Min Range: -3.8324

Max Act: 3.8324. Min Act: -0.1700

Data Index: 635205 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.8011. Min Act: -0.1700

Data Index: 1095806 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7698. Min Act: -0.1700

Data Index: 1166264 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7698. Min Act: -0.1700

Data Index: 1258963 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.8011. Min Act: -0.1700

Data Index: 210624 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7385. Min Act: -0.1700

Data Index: 1296441 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6759. Min Act: -0.1700

Data Index: 574097 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7698. Min Act: -0.1700

Data Index: 759749 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7385. Min Act: -0.1700

Data Index: 910799 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7072. Min Act: -0.1700

Data Index: 301433 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7072. Min Act: -0.1700

Data Index: 779202 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6759. Min Act: -0.1700

Data Index: 1497819 (Python Code)

Max Activating Token Index: 461

Text #12

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6759. Min Act: -0.1700

Data Index: 747594 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6759. Min Act: -0.1700

Data Index: 78749 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.7072. Min Act: -0.1700

Data Index: 574414 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6446. Min Act: -0.1700

Data Index: 466139 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6446. Min Act: -0.1700

Data Index: 318201 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6759. Min Act: -0.1700

Data Index: 930339 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6759. Min Act: -0.1700

Data Index: 413099 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 3.8324. Min Range: -3.8324

Max Act: 3.6759. Min Act: -0.1700

Data Index: 52696 (C4 (Web Text))

Max Activating Token Index: 236