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

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

Neuron 1574 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: 3.7550. Min Range: -3.7550

Max Act: 3.7550. Min Act: -0.1700

Data Index: 736193 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.7550. Min Act: -0.1700

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.7550. Min Act: -0.1700

Data Index: 1181786 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 428426 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6924. Min Act: -0.1700

Data Index: 611040 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 1340072 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6298. Min Act: -0.1700

Data Index: 1201925 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6298. Min Act: -0.1700

Data Index: 568495 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6298. Min Act: -0.1700

Data Index: 1223613 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 919542 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 581641 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 727759 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 757824 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6924. Min Act: -0.1700

Data Index: 762601 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 1080332 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.5985. Min Act: -0.1700

Data Index: 499415 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.5985. Min Act: -0.1700

Data Index: 644939 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.6611. Min Act: -0.1700

Data Index: 181424 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.5985. Min Act: -0.1700

Data Index: 303185 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 3.7550. Min Range: -3.7550

Max Act: 3.5985. Min Act: -0.1700

Data Index: 1116456 (C4 (Web Text))

Max Activating Token Index: 418