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

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

Neuron 709 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0062. Min Range: -4.0062

Max Act: 4.0062. Min Act: -0.1700

Data Index: 1296121 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9437. Min Act: -0.1700

Data Index: 456076 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9124. Min Act: -0.1700

Data Index: 397084 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9437. Min Act: -0.1700

Data Index: 799597 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9437. Min Act: -0.1700

Data Index: 507352 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9124. Min Act: -0.1700

Data Index: 528109 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9124. Min Act: -0.1700

Data Index: 79819 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9124. Min Act: -0.1700

Data Index: 149763 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 576187 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9124. Min Act: -0.1700

Data Index: 602902 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9124. Min Act: -0.1700

Data Index: 843045 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9437. Min Act: -0.1700

Data Index: 427585 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 428681 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.9124. Min Act: -0.1700

Data Index: 131175 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 175798 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 399355 (C4 (Web Text))

Max Activating Token Index: 733

Text #16

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 440716 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 246646 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 247829 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 4.0062. Min Range: -4.0062

Max Act: 3.8811. Min Act: -0.1700

Data Index: 256393 (C4 (Web Text))

Max Activating Token Index: 415