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

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

Neuron 694 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1640087 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1567797 (Python Code)

Max Activating Token Index: 186

Text #2

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1863. Min Act: -0.1700

Data Index: 1427455 (Python Code)

Max Activating Token Index: 206

Text #3

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1548. Min Act: -0.1700

Data Index: 1581323 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1706. Min Act: -0.1700

Data Index: 1459994 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1233. Min Act: -0.1700

Data Index: 1562360 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1076. Min Act: -0.1700

Data Index: 1444471 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0918. Min Act: -0.1700

Data Index: 1478289 (Python Code)

Max Activating Token Index: 806

Text #8

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1487307 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1632978 (Python Code)

Max Activating Token Index: 96

Text #10

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.1548. Min Act: -0.1700

Data Index: 1496019 (Python Code)

Max Activating Token Index: 257

Text #11

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0760. Min Act: -0.1700

Data Index: 1403297 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0918. Min Act: -0.1700

Data Index: 1426655 (Python Code)

Max Activating Token Index: 209

Text #13

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0918. Min Act: -0.1700

Data Index: 1377903 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1455642 (Python Code)

Max Activating Token Index: 292

Text #15

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0918. Min Act: -0.1700

Data Index: 1520933 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0760. Min Act: -0.1700

Data Index: 1391847 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1605207 (Python Code)

Max Activating Token Index: 813

Text #18

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1496774 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 3.1863. Min Range: -3.1863

Max Act: 3.0760. Min Act: -0.1700

Data Index: 1466945 (Python Code)

Max Activating Token Index: 683