Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1299 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.7370. Min Act: -0.1700

Data Index: 513626 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.6738. Min Act: -0.1700

Data Index: 231812 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.5669. Min Act: -0.1696

Data Index: 1486027 (Python Code)

Max Activating Token Index: 543

Text #3

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.5520. Min Act: -0.1700

Data Index: 1595405 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.5524. Min Act: -0.1697

Data Index: 1597364 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.5188. Min Act: -0.1698

Data Index: 1527177 (Python Code)

Max Activating Token Index: 838

Text #6

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.4740. Min Act: -0.1622

Data Index: 1421834 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.4681. Min Act: -0.1700

Data Index: 703100 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.4513. Min Act: -0.1698

Data Index: 1362438 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.4368. Min Act: -0.1700

Data Index: 1489454 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.4122. Min Act: -0.1696

Data Index: 1551345 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3605. Min Act: -0.1700

Data Index: 664669 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3845. Min Act: -0.1699

Data Index: 1435917 (Python Code)

Max Activating Token Index: 915

Text #13

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.4014. Min Act: -0.1699

Data Index: 1561498 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3903. Min Act: -0.1700

Data Index: 920101 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3518. Min Act: -0.1687

Data Index: 1578537 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3547. Min Act: -0.1700

Data Index: 1551095 (Python Code)

Max Activating Token Index: 388

Text #17

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3462. Min Act: -0.1700

Data Index: 1583204 (Python Code)

Max Activating Token Index: 737

Text #18

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3399. Min Act: -0.1688

Data Index: 1554985 (Python Code)

Max Activating Token Index: 942

Text #19

Max Range: 3.7370. Min Range: -3.7370

Max Act: 3.3417. Min Act: -0.1654

Data Index: 1446071 (Python Code)

Max Activating Token Index: 969