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

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

Neuron 12 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.7609. Min Act: -0.1700

Data Index: 1564570 (Python Code)

Max Activating Token Index: 213

Text #1

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.5731. Min Act: -0.1700

Data Index: 1622702 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.5104. Min Act: -0.1700

Data Index: 1365613 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1644125 (Python Code)

Max Activating Token Index: 834

Text #4

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1427857 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3850. Min Act: -0.1700

Data Index: 1608109 (Python Code)

Max Activating Token Index: 491

Text #6

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3850. Min Act: -0.1698

Data Index: 1635317 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.4477. Min Act: -0.1700

Data Index: 1435611 (Python Code)

Max Activating Token Index: 641

Text #8

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3850. Min Act: -0.1700

Data Index: 1413899 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1602834 (Python Code)

Max Activating Token Index: 484

Text #10

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1459461 (Python Code)

Max Activating Token Index: 285

Text #11

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1443352 (Python Code)

Max Activating Token Index: 216

Text #12

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3536. Min Act: -0.1700

Data Index: 1429768 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1409700 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1462633 (Python Code)

Max Activating Token Index: 530

Text #15

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1429107 (Python Code)

Max Activating Token Index: 297

Text #16

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.3222. Min Act: -0.1700

Data Index: 1536107 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1552042 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.2594. Min Act: -0.1698

Data Index: 1363512 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 3.7609. Min Range: -3.7609

Max Act: 3.2908. Min Act: -0.1700

Data Index: 1582301 (Python Code)

Max Activating Token Index: 179