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

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

Neuron 858 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: 5.8350. Min Range: -5.8350

Max Act: 5.8350. Min Act: -0.1700

Data Index: 967060 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.7725. Min Act: -0.1700

Data Index: 294599 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.6475. Min Act: -0.1700

Data Index: 699372 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.6475. Min Act: -0.1700

Data Index: 735442 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.5850. Min Act: -0.1700

Data Index: 576955 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.5538. Min Act: -0.1700

Data Index: 53435 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.4913. Min Act: -0.1700

Data Index: 98889 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.4600. Min Act: -0.1700

Data Index: 1253074 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.4913. Min Act: -0.1700

Data Index: 678518 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.3975. Min Act: -0.1700

Data Index: 814239 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.4288. Min Act: -0.1700

Data Index: 1123171 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.5225. Min Act: -0.1700

Data Index: 1258235 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.4600. Min Act: -0.1700

Data Index: 46580 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.3975. Min Act: -0.1700

Data Index: 31814 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.4913. Min Act: -0.1700

Data Index: 298771 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.3038. Min Act: -0.1700

Data Index: 723729 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.3350. Min Act: -0.1700

Data Index: 1317745 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.4288. Min Act: -0.1700

Data Index: 1138649 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.3663. Min Act: -0.1700

Data Index: 776928 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 5.8350. Min Range: -5.8350

Max Act: 5.3663. Min Act: -0.1700

Data Index: 12703 (C4 (Web Text))

Max Activating Token Index: 766