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

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

Neuron 1998 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.4666. Min Act: -0.1700

Data Index: 1423794 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.4353. Min Act: -0.1700

Data Index: 1439766 (Python Code)

Max Activating Token Index: 486

Text #2

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.4041. Min Act: -0.1700

Data Index: 1614370 (Python Code)

Max Activating Token Index: 412

Text #3

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.4666. Min Act: -0.1700

Data Index: 1379815 (Python Code)

Max Activating Token Index: 604

Text #4

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.3728. Min Act: -0.1700

Data Index: 1554116 (Python Code)

Max Activating Token Index: 377

Text #5

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.3728. Min Act: -0.1700

Data Index: 1606663 (Python Code)

Max Activating Token Index: 374

Text #6

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.4041. Min Act: -0.1700

Data Index: 1377484 (Python Code)

Max Activating Token Index: 531

Text #7

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.4041. Min Act: -0.1700

Data Index: 1501224 (Python Code)

Max Activating Token Index: 543

Text #8

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.3416. Min Act: -0.1700

Data Index: 1645864 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.3728. Min Act: -0.1700

Data Index: 1409588 (Python Code)

Max Activating Token Index: 285

Text #10

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.3728. Min Act: -0.1700

Data Index: 1526166 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.3103. Min Act: -0.1700

Data Index: 1501319 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2947. Min Act: -0.1700

Data Index: 1383886 (Python Code)

Max Activating Token Index: 550

Text #13

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.3103. Min Act: -0.1700

Data Index: 1651334 (Python Code)

Max Activating Token Index: 676

Text #14

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2634. Min Act: -0.1700

Data Index: 1427688 (Python Code)

Max Activating Token Index: 864

Text #15

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2634. Min Act: -0.1700

Data Index: 1378632 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2478. Min Act: -0.1700

Data Index: 1640656 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2791. Min Act: -0.1700

Data Index: 1493294 (Python Code)

Max Activating Token Index: 966

Text #18

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2478. Min Act: -0.1700

Data Index: 1498478 (Python Code)

Max Activating Token Index: 820

Text #19

Max Range: 5.4666. Min Range: -5.4666

Max Act: 5.2322. Min Act: -0.1700

Data Index: 1420455 (Python Code)

Max Activating Token Index: 790