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

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

Neuron 1230 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: 5.0517. Min Range: -5.0517

Max Act: 5.0517. Min Act: -0.1700

Data Index: 748740 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 5.0517. Min Range: -5.0517

Max Act: 5.0517. Min Act: -0.1700

Data Index: 1051153 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.9267. Min Act: -0.1700

Data Index: 575420 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.9579. Min Act: -0.1700

Data Index: 666015 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.8329. Min Act: -0.1700

Data Index: 244777 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.7704. Min Act: -0.1700

Data Index: 706245 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.7392. Min Act: -0.1700

Data Index: 269671 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.7392. Min Act: -0.1700

Data Index: 915107 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.7392. Min Act: -0.1700

Data Index: 138972 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6767. Min Act: -0.1700

Data Index: 127908 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6767. Min Act: -0.1700

Data Index: 1027188 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.7079. Min Act: -0.1700

Data Index: 78546 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6767. Min Act: -0.1700

Data Index: 818292 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6767. Min Act: -0.1700

Data Index: 1025291 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6767. Min Act: -0.1700

Data Index: 93360 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6142. Min Act: -0.1700

Data Index: 271929 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6142. Min Act: -0.1700

Data Index: 1218874 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.5829. Min Act: -0.1700

Data Index: 809403 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.6142. Min Act: -0.1700

Data Index: 941860 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 5.0517. Min Range: -5.0517

Max Act: 4.5829. Min Act: -0.1700

Data Index: 614721 (C4 (Web Text))

Max Activating Token Index: 809