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

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

Neuron 331 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.4650. Min Act: -0.1700

Data Index: 58797 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2150. Min Act: -0.1700

Data Index: 804857 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2150. Min Act: -0.1700

Data Index: 431221 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.1838. Min Act: -0.1700

Data Index: 528153 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.2775. Min Act: -0.1700

Data Index: 715988 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.1838. Min Act: -0.1700

Data Index: 347837 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.1525. Min Act: -0.1700

Data Index: 1173536 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.0588. Min Act: -0.1700

Data Index: 1233975 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.0588. Min Act: -0.1700

Data Index: 196037 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.1213. Min Act: -0.1700

Data Index: 1063232 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.0588. Min Act: -0.1700

Data Index: 1019824 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.0900. Min Act: -0.1700

Data Index: 1173876 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.0588. Min Act: -0.1700

Data Index: 340535 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 5.4650. Min Range: -5.4650

Max Act: 4.9650. Min Act: -0.1700

Data Index: 173019 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 5.4650. Min Range: -5.4650

Max Act: 4.9963. Min Act: -0.1700

Data Index: 891802 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 5.4650. Min Range: -5.4650

Max Act: 4.9338. Min Act: -0.1700

Data Index: 1174860 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.0275. Min Act: -0.1700

Data Index: 603481 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 5.4650. Min Range: -5.4650

Max Act: 4.9650. Min Act: -0.1700

Data Index: 1050229 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 5.4650. Min Range: -5.4650

Max Act: 4.9650. Min Act: -0.1700

Data Index: 115724 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 5.4650. Min Range: -5.4650

Max Act: 5.0275. Min Act: -0.1700

Data Index: 796278 (C4 (Web Text))

Max Activating Token Index: 673