Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 375 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2936. Min Act: -0.1700

Data Index: 4508679 (Open Web Text)

Max Activating Token Index: 869

Text #1

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2962. Min Act: -0.1700

Data Index: 1456050 (Open Web Text)

Max Activating Token Index: 917

Text #2

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.3018. Min Act: -0.1700

Data Index: 2920960 (Open Web Text)

Max Activating Token Index: 453

Text #3

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.3029. Min Act: -0.1700

Data Index: 6568914 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2827. Min Act: -0.1700

Data Index: 4711884 (Open Web Text)

Max Activating Token Index: 704

Text #5

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2821. Min Act: -0.1700

Data Index: 2552237 (Open Web Text)

Max Activating Token Index: 854

Text #6

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2759. Min Act: -0.1700

Data Index: 3149828 (Open Web Text)

Max Activating Token Index: 626

Text #7

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2867. Min Act: -0.1700

Data Index: 6340514 (Open Web Text)

Max Activating Token Index: 46

Text #8

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2784. Min Act: -0.1700

Data Index: 1634572 (Open Web Text)

Max Activating Token Index: 663

Text #9

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2886. Min Act: -0.1700

Data Index: 3966724 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2709. Min Act: -0.1700

Data Index: 4001670 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2698. Min Act: -0.1700

Data Index: 4338136 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2612. Min Act: -0.1700

Data Index: 5754836 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2618. Min Act: -0.1700

Data Index: 5717168 (Open Web Text)

Max Activating Token Index: 736

Text #14

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2674. Min Act: -0.1700

Data Index: 5196134 (Open Web Text)

Max Activating Token Index: 359

Text #15

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2590. Min Act: -0.1700

Data Index: 2003076 (Open Web Text)

Max Activating Token Index: 570

Text #16

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2632. Min Act: -0.1700

Data Index: 1809642 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2599. Min Act: -0.1700

Data Index: 4932562 (Open Web Text)

Max Activating Token Index: 901

Text #18

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2577. Min Act: -0.1700

Data Index: 4802377 (Open Web Text)

Max Activating Token Index: 795

Text #19

Max Range: 3.3029. Min Range: -3.3029

Max Act: 3.2606. Min Act: -0.1700

Data Index: 1154392 (Open Web Text)

Max Activating Token Index: 20