Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1951 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.1090. Min Range: -4.1090

Max Act: 4.1090. Min Act: -0.1700

Data Index: 1212307 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.9840. Min Act: -0.1700

Data Index: 1186674 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.9214. Min Act: -0.1700

Data Index: 666682 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8902. Min Act: -0.1700

Data Index: 900669 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7963. Min Act: -0.1700

Data Index: 1157619 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8276. Min Act: -0.1700

Data Index: 301043 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8276. Min Act: -0.1700

Data Index: 18840 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8276. Min Act: -0.1700

Data Index: 1206437 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8276. Min Act: -0.1700

Data Index: 1064928 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7650. Min Act: -0.1700

Data Index: 1204165 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8276. Min Act: -0.1700

Data Index: 25926 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8276. Min Act: -0.1700

Data Index: 697129 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.8276. Min Act: -0.1700

Data Index: 640772 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7963. Min Act: -0.1700

Data Index: 177911 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7650. Min Act: -0.1700

Data Index: 8654 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7963. Min Act: -0.1700

Data Index: 372026 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7650. Min Act: -0.1700

Data Index: 254993 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7650. Min Act: -0.1700

Data Index: 1095265 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7025. Min Act: -0.1700

Data Index: 772095 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 4.1090. Min Range: -4.1090

Max Act: 3.7338. Min Act: -0.1700

Data Index: 1224680 (C4 (Web Text))

Max Activating Token Index: 543