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

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

Neuron 1028 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: 3.6264. Min Range: -3.6264

Max Act: 3.6264. Min Act: -0.1699

Data Index: 1631557 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.3286. Min Act: -0.1614

Data Index: 1529340 (Python Code)

Max Activating Token Index: 527

Text #2

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.2815. Min Act: -0.1675

Data Index: 1594855 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.2658. Min Act: -0.1700

Data Index: 1558981 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.2186. Min Act: -0.1700

Data Index: 1623870 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.2344. Min Act: -0.1688

Data Index: 1532239 (Python Code)

Max Activating Token Index: 343

Text #6

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.2344. Min Act: -0.1700

Data Index: 1524261 (Python Code)

Max Activating Token Index: 110

Text #7

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.2029. Min Act: -0.1700

Data Index: 1564872 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.2029. Min Act: -0.1627

Data Index: 1407764 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1872. Min Act: -0.1697

Data Index: 1499837 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1714. Min Act: -0.1700

Data Index: 1487768 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1714. Min Act: -0.1700

Data Index: 1466233 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1714. Min Act: -0.1700

Data Index: 1424489 (Python Code)

Max Activating Token Index: 556

Text #13

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1484811 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1484710 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1557. Min Act: -0.1699

Data Index: 1615862 (Python Code)

Max Activating Token Index: 888

Text #16

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1557. Min Act: -0.1698

Data Index: 1376142 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1872. Min Act: -0.1700

Data Index: 1531714 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1595168 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 3.6264. Min Range: -3.6264

Max Act: 3.1242. Min Act: -0.1699

Data Index: 1452330 (Python Code)

Max Activating Token Index: 10