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

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

Neuron 451 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.3534. Min Act: -0.1700

Data Index: 83972 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.1963. Min Act: -0.1700

Data Index: 323981 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.1648. Min Act: -0.1700

Data Index: 685511 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.1648. Min Act: -0.1700

Data Index: 1341428 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.1648. Min Act: -0.1700

Data Index: 1123752 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.1648. Min Act: -0.1700

Data Index: 1353366 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.1491. Min Act: -0.1700

Data Index: 96780 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.0545. Min Act: -0.1700

Data Index: 89599 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.0387. Min Act: -0.1700

Data Index: 1163741 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.0545. Min Act: -0.1700

Data Index: 624665 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.0545. Min Act: -0.1700

Data Index: 17528 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.0229. Min Act: -0.1700

Data Index: 1315313 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 3.3534. Min Range: -3.3534

Max Act: 2.9913. Min Act: -0.1700

Data Index: 1311554 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.3534. Min Range: -3.3534

Max Act: 3.0071. Min Act: -0.1700

Data Index: 936348 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.3534. Min Range: -3.3534

Max Act: 2.9913. Min Act: -0.1700

Data Index: 587181 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 3.3534. Min Range: -3.3534

Max Act: 2.9913. Min Act: -0.1700

Data Index: 582690 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 3.3534. Min Range: -3.3534

Max Act: 2.9755. Min Act: -0.1700

Data Index: 436830 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 3.3534. Min Range: -3.3534

Max Act: 2.9755. Min Act: -0.1700

Data Index: 589932 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 3.3534. Min Range: -3.3534

Max Act: 2.9913. Min Act: -0.1700

Data Index: 46828 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 3.3534. Min Range: -3.3534

Max Act: 2.9913. Min Act: -0.1700

Data Index: 466256 (C4 (Web Text))

Max Activating Token Index: 165