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

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

Neuron 1709 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: 7.5778. Min Range: -7.5778

Max Act: 7.5778. Min Act: -0.1700

Data Index: 791027 (C4 (Web Text))

Max Activating Token Index: 615

Text #1

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.4528. Min Act: -0.1700

Data Index: 387902 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.3278. Min Act: -0.1700

Data Index: 482255 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.3903. Min Act: -0.1700

Data Index: 945755 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.3903. Min Act: -0.1700

Data Index: 179959 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.3903. Min Act: -0.1700

Data Index: 364921 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.3903. Min Act: -0.1700

Data Index: 402376 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.3278. Min Act: -0.1700

Data Index: 822883 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.2028. Min Act: -0.1700

Data Index: 268571 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.4528. Min Act: -0.1700

Data Index: 457880 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.3278. Min Act: -0.1700

Data Index: 15212 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.2340. Min Act: -0.1700

Data Index: 226049 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.1090. Min Act: -0.1700

Data Index: 914197 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.1090. Min Act: -0.1700

Data Index: 1341270 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.2653. Min Act: -0.1700

Data Index: 398945 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.2028. Min Act: -0.1700

Data Index: 295882 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.1715. Min Act: -0.1700

Data Index: 564261 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.1090. Min Act: -0.1700

Data Index: 430378 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.2028. Min Act: -0.1700

Data Index: 1089213 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 7.5778. Min Range: -7.5778

Max Act: 7.2340. Min Act: -0.1700

Data Index: 1165151 (C4 (Web Text))

Max Activating Token Index: 1004