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

Dataset: Open Web Text

Neuron 669 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: 4.1788. Min Range: -4.1788

Max Act: 4.1788. Min Act: -0.1700

Data Index: 679202 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.1741. Min Act: -0.1700

Data Index: 7085690 (Open Web Text)

Max Activating Token Index: 313

Text #2

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.1375. Min Act: -0.1700

Data Index: 3394255 (Open Web Text)

Max Activating Token Index: 973

Text #3

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.1433. Min Act: -0.1700

Data Index: 6126323 (Open Web Text)

Max Activating Token Index: 991

Text #4

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0863. Min Act: -0.1700

Data Index: 3857193 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.1249. Min Act: -0.1700

Data Index: 8811130 (Open Web Text)

Max Activating Token Index: 748

Text #6

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.1259. Min Act: -0.1700

Data Index: 1092064 (Open Web Text)

Max Activating Token Index: 929

Text #7

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0943. Min Act: -0.1700

Data Index: 5945628 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0975. Min Act: -0.1700

Data Index: 2492444 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0646. Min Act: -0.1700

Data Index: 5093071 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0807. Min Act: -0.1700

Data Index: 1926620 (Open Web Text)

Max Activating Token Index: 540

Text #11

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0979. Min Act: -0.1700

Data Index: 4325051 (Open Web Text)

Max Activating Token Index: 827

Text #12

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0432. Min Act: -0.1700

Data Index: 5069255 (Open Web Text)

Max Activating Token Index: 585

Text #13

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0479. Min Act: -0.1700

Data Index: 4895544 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0499. Min Act: -0.1700

Data Index: 1926622 (Open Web Text)

Max Activating Token Index: 955

Text #15

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0236. Min Act: -0.1700

Data Index: 2894717 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0418. Min Act: -0.1700

Data Index: 952289 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0416. Min Act: -0.1700

Data Index: 3780908 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0110. Min Act: -0.1700

Data Index: 2460503 (Open Web Text)

Max Activating Token Index: 866

Text #19

Max Range: 4.1788. Min Range: -4.1788

Max Act: 4.0239. Min Act: -0.1700

Data Index: 3080213 (Open Web Text)

Max Activating Token Index: 842