Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 322 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.3075. Min Act: -0.1700

Data Index: 605900 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2447. Min Act: -0.1700

Data Index: 659001 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2447. Min Act: -0.1700

Data Index: 516864 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2289. Min Act: -0.1700

Data Index: 30219 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.2132. Min Act: -0.1700

Data Index: 514620 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1975. Min Act: -0.1700

Data Index: 783114 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1817. Min Act: -0.1700

Data Index: 605585 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1817. Min Act: -0.1700

Data Index: 19891 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1660. Min Act: -0.1700

Data Index: 954935 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1817. Min Act: -0.1700

Data Index: 1119599 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1660. Min Act: -0.1700

Data Index: 327615 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1660. Min Act: -0.1700

Data Index: 376517 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1660. Min Act: -0.1700

Data Index: 1264507 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1503. Min Act: -0.1700

Data Index: 1193246 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1503. Min Act: -0.1700

Data Index: 83840 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1503. Min Act: -0.1700

Data Index: 133746 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1503. Min Act: -0.1700

Data Index: 614550 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1503. Min Act: -0.1700

Data Index: 368058 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1114293 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 3.3075. Min Range: -3.3075

Max Act: 3.1345. Min Act: -0.1700

Data Index: 1220445 (C4 (Web Text))

Max Activating Token Index: 28