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

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

Neuron 1672 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.2869. Min Act: -0.1700

Data Index: 1553515 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.2397. Min Act: -0.1700

Data Index: 1543837 (Python Code)

Max Activating Token Index: 479

Text #2

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1465839 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1514075 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1443731 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.1453. Min Act: -0.1700

Data Index: 1570804 (Python Code)

Max Activating Token Index: 334

Text #6

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1529836 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1426602 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0823. Min Act: -0.1700

Data Index: 1481406 (Python Code)

Max Activating Token Index: 979

Text #9

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0665. Min Act: -0.1700

Data Index: 1623939 (Python Code)

Max Activating Token Index: 768

Text #10

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1375035 (Python Code)

Max Activating Token Index: 403

Text #11

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0191. Min Act: -0.1700

Data Index: 1417763 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1433103 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0033. Min Act: -0.1700

Data Index: 1563028 (Python Code)

Max Activating Token Index: 352

Text #14

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0191. Min Act: -0.1700

Data Index: 1469250 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1447344 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 3.2869. Min Range: -3.2869

Max Act: 2.9717. Min Act: -0.1700

Data Index: 1400675 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0191. Min Act: -0.1700

Data Index: 1439656 (Python Code)

Max Activating Token Index: 266

Text #18

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0033. Min Act: -0.1700

Data Index: 1390986 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 3.2869. Min Range: -3.2869

Max Act: 3.0349. Min Act: -0.1700

Data Index: 1518287 (Python Code)

Max Activating Token Index: 68