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

Dataset: Open Web Text

Neuron 1642 in Layer 3

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: 3.7743. Min Range: -3.7743

Max Act: 3.7743. Min Act: -0.1700

Data Index: 8617709 (Open Web Text)

Max Activating Token Index: 175

Text #1

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.6171. Min Act: -0.1700

Data Index: 7796966 (Open Web Text)

Max Activating Token Index: 972

Text #2

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5871. Min Act: -0.1700

Data Index: 242752 (Open Web Text)

Max Activating Token Index: 916

Text #3

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5625. Min Act: -0.1700

Data Index: 529461 (Open Web Text)

Max Activating Token Index: 379

Text #4

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5413. Min Act: -0.1700

Data Index: 5055817 (Open Web Text)

Max Activating Token Index: 772

Text #5

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5651. Min Act: -0.1700

Data Index: 3511513 (Open Web Text)

Max Activating Token Index: 649

Text #6

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5717. Min Act: -0.1700

Data Index: 8059064 (Open Web Text)

Max Activating Token Index: 656

Text #7

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5431. Min Act: -0.1700

Data Index: 6801060 (Open Web Text)

Max Activating Token Index: 252

Text #8

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5059. Min Act: -0.1700

Data Index: 8774116 (Open Web Text)

Max Activating Token Index: 316

Text #9

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5320. Min Act: -0.1700

Data Index: 7239374 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5256. Min Act: -0.1700

Data Index: 2359590 (Open Web Text)

Max Activating Token Index: 199

Text #11

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.4913. Min Act: -0.1700

Data Index: 3366543 (Open Web Text)

Max Activating Token Index: 945

Text #12

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.4934. Min Act: -0.1700

Data Index: 884668 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5184. Min Act: -0.1700

Data Index: 2329535 (Open Web Text)

Max Activating Token Index: 121

Text #14

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.5076. Min Act: -0.1700

Data Index: 1322930 (Open Web Text)

Max Activating Token Index: 570

Text #15

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.4824. Min Act: -0.1700

Data Index: 3166424 (Open Web Text)

Max Activating Token Index: 648

Text #16

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.4601. Min Act: -0.1700

Data Index: 8446455 (Open Web Text)

Max Activating Token Index: 62

Text #17

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.4968. Min Act: -0.1700

Data Index: 3778880 (Open Web Text)

Max Activating Token Index: 723

Text #18

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.4838. Min Act: -0.1700

Data Index: 398047 (Open Web Text)

Max Activating Token Index: 493

Text #19

Max Range: 3.7743. Min Range: -3.7743

Max Act: 3.4943. Min Act: -0.1700

Data Index: 4213956 (Open Web Text)

Max Activating Token Index: 729