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

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

Neuron 1363 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: 5.8395. Min Range: -5.8395

Max Act: 5.8395. Min Act: -0.1700

Data Index: 1254889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.5895. Min Act: -0.1700

Data Index: 1432994 (Python Code)

Max Activating Token Index: 567

Text #2

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.5895. Min Act: -0.1700

Data Index: 1531098 (Python Code)

Max Activating Token Index: 273

Text #3

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.5582. Min Act: -0.1700

Data Index: 1515792 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.5270. Min Act: -0.1700

Data Index: 1008438 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.5270. Min Act: -0.1700

Data Index: 1473752 (Python Code)

Max Activating Token Index: 68

Text #6

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4957. Min Act: -0.1700

Data Index: 570738 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4957. Min Act: -0.1700

Data Index: 1343654 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4957. Min Act: -0.1700

Data Index: 1567819 (Python Code)

Max Activating Token Index: 438

Text #9

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4645. Min Act: -0.1700

Data Index: 1552549 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4957. Min Act: -0.1700

Data Index: 1534428 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4957. Min Act: -0.1700

Data Index: 374457 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4332. Min Act: -0.1700

Data Index: 283156 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4645. Min Act: -0.1700

Data Index: 1432238 (Python Code)

Max Activating Token Index: 715

Text #14

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4332. Min Act: -0.1700

Data Index: 1550497 (Python Code)

Max Activating Token Index: 464

Text #15

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4645. Min Act: -0.1700

Data Index: 1628611 (Python Code)

Max Activating Token Index: 853

Text #16

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4645. Min Act: -0.1700

Data Index: 217249 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4645. Min Act: -0.1700

Data Index: 57383 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.4645. Min Act: -0.1700

Data Index: 1395192 (Python Code)

Max Activating Token Index: 210

Text #19

Max Range: 5.8395. Min Range: -5.8395

Max Act: 5.3707. Min Act: -0.1700

Data Index: 1486452 (Python Code)

Max Activating Token Index: 1023