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

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

Neuron 2010 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: 3.2571. Min Range: -3.2571

Max Act: 3.2571. Min Act: -0.1700

Data Index: 746437 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.2257. Min Act: -0.1700

Data Index: 1272928 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.2257. Min Act: -0.1700

Data Index: 1396955 (Python Code)

Max Activating Token Index: 802

Text #3

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 1084227 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.2257. Min Act: -0.1700

Data Index: 1105422 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.2257. Min Act: -0.1700

Data Index: 1324620 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.2571. Min Act: -0.1700

Data Index: 735895 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.2257. Min Act: -0.1700

Data Index: 205156 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 628783 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1627. Min Act: -0.1700

Data Index: 1459234 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 1521968 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 1561865 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 1367714 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 1397211 (Python Code)

Max Activating Token Index: 875

Text #14

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1627. Min Act: -0.1700

Data Index: 683071 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 428531 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 345792 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 746568 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1627. Min Act: -0.1700

Data Index: 769248 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 3.2571. Min Range: -3.2571

Max Act: 3.1942. Min Act: -0.1700

Data Index: 1076846 (C4 (Web Text))

Max Activating Token Index: 862