Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 888 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.9936. Min Act: -0.1689

Data Index: 1600282 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.9258. Min Act: -0.1698

Data Index: 1652554 (Python Code)

Max Activating Token Index: 554

Text #2

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8918. Min Act: -0.1675

Data Index: 1590881 (Python Code)

Max Activating Token Index: 469

Text #3

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8747. Min Act: -0.1699

Data Index: 1587007 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8576. Min Act: -0.1700

Data Index: 1392968 (Python Code)

Max Activating Token Index: 847

Text #5

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8405. Min Act: -0.1697

Data Index: 1417209 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8405. Min Act: -0.1698

Data Index: 1485870 (Python Code)

Max Activating Token Index: 386

Text #7

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8405. Min Act: -0.1645

Data Index: 1440107 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8234. Min Act: -0.1697

Data Index: 1387804 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8234. Min Act: -0.1700

Data Index: 1594453 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8148. Min Act: -0.1700

Data Index: 1607449 (Python Code)

Max Activating Token Index: 533

Text #11

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.7976. Min Act: -0.1625

Data Index: 1645567 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8062. Min Act: -0.1700

Data Index: 1431985 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8062. Min Act: -0.1700

Data Index: 1491574 (Python Code)

Max Activating Token Index: 400

Text #14

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.8062. Min Act: -0.1698

Data Index: 1608747 (Python Code)

Max Activating Token Index: 570

Text #15

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.7976. Min Act: -0.1700

Data Index: 1627355 (Python Code)

Max Activating Token Index: 715

Text #16

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.7804. Min Act: -0.1700

Data Index: 1425109 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.7890. Min Act: -0.1700

Data Index: 1587442 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.7804. Min Act: -0.1700

Data Index: 1389425 (Python Code)

Max Activating Token Index: 321

Text #19

Max Range: 1.9936. Min Range: -1.9936

Max Act: 1.7804. Min Act: -0.1698

Data Index: 1656828 (Python Code)

Max Activating Token Index: 696