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

Dataset: Open Web Text

Neuron 692 in Layer 4

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: 4.7730. Min Range: -4.7730

Max Act: 4.7730. Min Act: -0.1700

Data Index: 1460955 (Open Web Text)

Max Activating Token Index: 290

Text #1

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.7687. Min Act: -0.1700

Data Index: 107552 (Open Web Text)

Max Activating Token Index: 659

Text #2

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.6884. Min Act: -0.1700

Data Index: 5759176 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.6583. Min Act: -0.1700

Data Index: 2923257 (Open Web Text)

Max Activating Token Index: 612

Text #4

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.6625. Min Act: -0.1700

Data Index: 5947122 (Open Web Text)

Max Activating Token Index: 550

Text #5

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.6495. Min Act: -0.1700

Data Index: 7728956 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.6460. Min Act: -0.1700

Data Index: 1829799 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.6061. Min Act: -0.1700

Data Index: 2085919 (Open Web Text)

Max Activating Token Index: 141

Text #8

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.5976. Min Act: -0.1700

Data Index: 2837055 (Open Web Text)

Max Activating Token Index: 788

Text #9

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.5776. Min Act: -0.1700

Data Index: 2688901 (Open Web Text)

Max Activating Token Index: 124

Text #10

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.5500. Min Act: -0.1700

Data Index: 5769220 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.5557. Min Act: -0.1700

Data Index: 4057673 (Open Web Text)

Max Activating Token Index: 394

Text #12

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.5095. Min Act: -0.1700

Data Index: 6056989 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.5133. Min Act: -0.1700

Data Index: 501162 (Open Web Text)

Max Activating Token Index: 887

Text #14

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.4866. Min Act: -0.1700

Data Index: 4554323 (Open Web Text)

Max Activating Token Index: 990

Text #15

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.4436. Min Act: -0.1700

Data Index: 4468094 (Open Web Text)

Max Activating Token Index: 188

Text #16

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.4848. Min Act: -0.1700

Data Index: 6308407 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.4434. Min Act: -0.1700

Data Index: 1092061 (Open Web Text)

Max Activating Token Index: 602

Text #18

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.4796. Min Act: -0.1700

Data Index: 2184691 (Open Web Text)

Max Activating Token Index: 369

Text #19

Max Range: 4.7730. Min Range: -4.7730

Max Act: 4.4429. Min Act: -0.1700

Data Index: 5648139 (Open Web Text)

Max Activating Token Index: 396