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

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

Neuron 710 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.9200. Min Act: -0.1700

Data Index: 609960 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.9200. Min Act: -0.1700

Data Index: 726454 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.7638. Min Act: -0.1700

Data Index: 888088 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.7325. Min Act: -0.1700

Data Index: 1079181 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.7013. Min Act: -0.1700

Data Index: 866844 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.6700. Min Act: -0.1700

Data Index: 1079550 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.6700. Min Act: -0.1700

Data Index: 198051 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.6075. Min Act: -0.1700

Data Index: 1305119 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.6388. Min Act: -0.1700

Data Index: 782368 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.5763. Min Act: -0.1700

Data Index: 1343671 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4513. Min Act: -0.1700

Data Index: 416635 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4825. Min Act: -0.1700

Data Index: 657976 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4825. Min Act: -0.1700

Data Index: 471168 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4513. Min Act: -0.1700

Data Index: 1056124 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4825. Min Act: -0.1700

Data Index: 97580 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4513. Min Act: -0.1700

Data Index: 470748 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4513. Min Act: -0.1700

Data Index: 880053 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.4825. Min Act: -0.1700

Data Index: 1239059 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.3888. Min Act: -0.1700

Data Index: 1007970 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 5.9200. Min Range: -5.9200

Max Act: 5.3888. Min Act: -0.1700

Data Index: 1320521 (C4 (Web Text))

Max Activating Token Index: 317