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

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

Neuron 346 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: 5.3571. Min Range: -5.3571

Max Act: 5.3571. Min Act: -0.1700

Data Index: 413573 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.2009. Min Act: -0.1700

Data Index: 1197604 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.1696. Min Act: -0.1700

Data Index: 489141 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.0446. Min Act: -0.1700

Data Index: 1179816 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.2009. Min Act: -0.1700

Data Index: 514339 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.0759. Min Act: -0.1700

Data Index: 1310360 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.1696. Min Act: -0.1700

Data Index: 376601 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.1696. Min Act: -0.1700

Data Index: 598466 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 5.3571. Min Range: -5.3571

Max Act: 4.9196. Min Act: -0.1700

Data Index: 334095 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.0446. Min Act: -0.1700

Data Index: 1153994 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.0446. Min Act: -0.1700

Data Index: 422938 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.0446. Min Act: -0.1700

Data Index: 338205 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.0134. Min Act: -0.1700

Data Index: 585215 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 5.3571. Min Range: -5.3571

Max Act: 4.9821. Min Act: -0.1700

Data Index: 1255202 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 5.3571. Min Range: -5.3571

Max Act: 4.9509. Min Act: -0.1700

Data Index: 516996 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 5.3571. Min Range: -5.3571

Max Act: 4.9821. Min Act: -0.1700

Data Index: 1000130 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 5.3571. Min Range: -5.3571

Max Act: 4.8884. Min Act: -0.1700

Data Index: 951477 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 5.3571. Min Range: -5.3571

Max Act: 4.8884. Min Act: -0.1700

Data Index: 1304585 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 5.3571. Min Range: -5.3571

Max Act: 4.8884. Min Act: -0.1700

Data Index: 844417 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 5.3571. Min Range: -5.3571

Max Act: 5.0134. Min Act: -0.1700

Data Index: 111012 (C4 (Web Text))

Max Activating Token Index: 979