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

Dataset: Open Web Text

Neuron 1691 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: 2.0601. Min Range: -2.0601

Max Act: 2.0601. Min Act: -0.1700

Data Index: 7575368 (Open Web Text)

Max Activating Token Index: 246

Text #1

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0179. Min Act: -0.1699

Data Index: 7575367 (Open Web Text)

Max Activating Token Index: 1001

Text #2

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0100. Min Act: -0.1700

Data Index: 4555340 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0139. Min Act: -0.1700

Data Index: 8153645 (Open Web Text)

Max Activating Token Index: 171

Text #4

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9936. Min Act: -0.1698

Data Index: 4415321 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 2.0601. Min Range: -2.0601

Max Act: 2.0058. Min Act: -0.1700

Data Index: 6076014 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9928. Min Act: -0.1692

Data Index: 344413 (Open Web Text)

Max Activating Token Index: 281

Text #7

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9915. Min Act: -0.1700

Data Index: 135257 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9901. Min Act: -0.1700

Data Index: 8055620 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9732. Min Act: -0.1700

Data Index: 7416862 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9749. Min Act: -0.1700

Data Index: 3305912 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9748. Min Act: -0.1700

Data Index: 3976767 (Open Web Text)

Max Activating Token Index: 685

Text #12

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9718. Min Act: -0.1700

Data Index: 1924139 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9680. Min Act: -0.1700

Data Index: 4535558 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9720. Min Act: -0.1700

Data Index: 8395726 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9606. Min Act: -0.1700

Data Index: 2480711 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9497. Min Act: -0.1700

Data Index: 5116472 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9526. Min Act: -0.1694

Data Index: 6172924 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9510. Min Act: -0.1700

Data Index: 4459988 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.0601. Min Range: -2.0601

Max Act: 1.9493. Min Act: -0.1700

Data Index: 4665504 (Open Web Text)

Max Activating Token Index: 6