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

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

Neuron 468 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1574838 (Python Code)

Max Activating Token Index: 627

Text #1

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.2362. Min Act: -0.1700

Data Index: 1578246 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.2362. Min Act: -0.1700

Data Index: 1488626 (Python Code)

Max Activating Token Index: 619

Text #3

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1890. Min Act: -0.1700

Data Index: 1629453 (Python Code)

Max Activating Token Index: 379

Text #4

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1732. Min Act: -0.1700

Data Index: 989420 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1890. Min Act: -0.1700

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1575. Min Act: -0.1700

Data Index: 1385334 (Python Code)

Max Activating Token Index: 509

Text #7

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1575. Min Act: -0.1700

Data Index: 1534988 (Python Code)

Max Activating Token Index: 649

Text #8

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1732. Min Act: -0.1700

Data Index: 1419267 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1732. Min Act: -0.1700

Data Index: 1245655 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1102. Min Act: -0.1700

Data Index: 1566121 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1418. Min Act: -0.1700

Data Index: 12764 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1418. Min Act: -0.1700

Data Index: 1427493 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.2204. Min Act: -0.1700

Data Index: 1628144 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1260. Min Act: -0.1700

Data Index: 1465251 (Python Code)

Max Activating Token Index: 862

Text #15

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1260. Min Act: -0.1700

Data Index: 624235 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1102. Min Act: -0.1700

Data Index: 722316 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1260. Min Act: -0.1700

Data Index: 1515395 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1102. Min Act: -0.1700

Data Index: 1412562 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 3.3304. Min Range: -3.3304

Max Act: 3.1102. Min Act: -0.1700

Data Index: 1396006 (Python Code)

Max Activating Token Index: 966