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

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

Neuron 97 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: 3.6351. Min Range: -3.6351

Max Act: 3.5725. Min Act: -0.1700

Data Index: 1650811 (Python Code)

Max Activating Token Index: 378

Text #1

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.6351. Min Act: -0.1700

Data Index: 1527968 (Python Code)

Max Activating Token Index: 803

Text #2

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5255. Min Act: -0.1700

Data Index: 1364185 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5255. Min Act: -0.1700

Data Index: 1542348 (Python Code)

Max Activating Token Index: 599

Text #4

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1372284 (Python Code)

Max Activating Token Index: 882

Text #5

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4628. Min Act: -0.1700

Data Index: 920525 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4785. Min Act: -0.1700

Data Index: 1605761 (Python Code)

Max Activating Token Index: 656

Text #7

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5255. Min Act: -0.1700

Data Index: 1508835 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1433153 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4471. Min Act: -0.1700

Data Index: 311528 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4941. Min Act: -0.1700

Data Index: 1449376 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1518908 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1583215 (Python Code)

Max Activating Token Index: 861

Text #13

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4941. Min Act: -0.1700

Data Index: 1584752 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1375031 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4471. Min Act: -0.1700

Data Index: 1553943 (Python Code)

Max Activating Token Index: 857

Text #16

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4785. Min Act: -0.1700

Data Index: 1396782 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5255. Min Act: -0.1700

Data Index: 1417557 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.4628. Min Act: -0.1700

Data Index: 1522169 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 3.6351. Min Range: -3.6351

Max Act: 3.5098. Min Act: -0.1700

Data Index: 1520792 (Python Code)

Max Activating Token Index: 861