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

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

Neuron 873 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: 5.1192. Min Range: -5.1192

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1625469 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 5.1192. Min Range: -5.1192

Max Act: 5.0567. Min Act: -0.1700

Data Index: 1432394 (Python Code)

Max Activating Token Index: 326

Text #2

Max Range: 5.1192. Min Range: -5.1192

Max Act: 5.0567. Min Act: -0.1700

Data Index: 1631084 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 5.1192. Min Range: -5.1192

Max Act: 5.1192. Min Act: -0.1700

Data Index: 1464915 (Python Code)

Max Activating Token Index: 605

Text #4

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1410540 (Python Code)

Max Activating Token Index: 831

Text #5

Max Range: 5.1192. Min Range: -5.1192

Max Act: 5.0254. Min Act: -0.1700

Data Index: 1585786 (Python Code)

Max Activating Token Index: 379

Text #6

Max Range: 5.1192. Min Range: -5.1192

Max Act: 5.0879. Min Act: -0.1700

Data Index: 1603865 (Python Code)

Max Activating Token Index: 339

Text #7

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1589427 (Python Code)

Max Activating Token Index: 245

Text #8

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1408944 (Python Code)

Max Activating Token Index: 200

Text #9

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9629. Min Act: -0.1700

Data Index: 1465435 (Python Code)

Max Activating Token Index: 707

Text #10

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1399516 (Python Code)

Max Activating Token Index: 482

Text #11

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1542585 (Python Code)

Max Activating Token Index: 62

Text #12

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1365398 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1615602 (Python Code)

Max Activating Token Index: 446

Text #14

Max Range: 5.1192. Min Range: -5.1192

Max Act: 5.0254. Min Act: -0.1700

Data Index: 1597847 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1445359 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1465643 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1453718 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9629. Min Act: -0.1700

Data Index: 1596845 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 5.1192. Min Range: -5.1192

Max Act: 4.9942. Min Act: -0.1700

Data Index: 1469286 (Python Code)

Max Activating Token Index: 7