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

Dataset: Open Web Text

Neuron 236 in Layer 5

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: 4.7797. Min Range: -4.7797

Max Act: 4.7618. Min Act: -0.1700

Data Index: 2082998 (Open Web Text)

Max Activating Token Index: 807

Text #1

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.7797. Min Act: -0.1700

Data Index: 6747463 (Open Web Text)

Max Activating Token Index: 914

Text #2

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.7175. Min Act: -0.1700

Data Index: 3109191 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.6697. Min Act: -0.1700

Data Index: 4170121 (Open Web Text)

Max Activating Token Index: 329

Text #4

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.6071. Min Act: -0.1700

Data Index: 329948 (Open Web Text)

Max Activating Token Index: 892

Text #5

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5654. Min Act: -0.1700

Data Index: 2821580 (Open Web Text)

Max Activating Token Index: 875

Text #6

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5993. Min Act: -0.1700

Data Index: 4130184 (Open Web Text)

Max Activating Token Index: 876

Text #7

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5719. Min Act: -0.1700

Data Index: 3335717 (Open Web Text)

Max Activating Token Index: 508

Text #8

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5624. Min Act: -0.1700

Data Index: 2091539 (Open Web Text)

Max Activating Token Index: 702

Text #9

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5647. Min Act: -0.1700

Data Index: 4323995 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.4827. Min Act: -0.1700

Data Index: 2338214 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.4942. Min Act: -0.1700

Data Index: 224069 (Open Web Text)

Max Activating Token Index: 427

Text #12

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.4994. Min Act: -0.1700

Data Index: 2226766 (Open Web Text)

Max Activating Token Index: 694

Text #13

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.4676. Min Act: -0.1700

Data Index: 1377985 (Open Web Text)

Max Activating Token Index: 848

Text #14

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.4663. Min Act: -0.1700

Data Index: 1721474 (Open Web Text)

Max Activating Token Index: 935

Text #15

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5081. Min Act: -0.1700

Data Index: 3912154 (Open Web Text)

Max Activating Token Index: 911

Text #16

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.4503. Min Act: -0.1700

Data Index: 2347384 (Open Web Text)

Max Activating Token Index: 985

Text #17

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5000. Min Act: -0.1700

Data Index: 3664852 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5061. Min Act: -0.1700

Data Index: 1906711 (Open Web Text)

Max Activating Token Index: 705

Text #19

Max Range: 4.7797. Min Range: -4.7797

Max Act: 4.5178. Min Act: -0.1700

Data Index: 4292432 (Open Web Text)

Max Activating Token Index: 735