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

Dataset: Open Web Text

Neuron 986 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: 4.0586. Min Range: -4.0586

Max Act: 4.0586. Min Act: -0.1700

Data Index: 868775 (Open Web Text)

Max Activating Token Index: 846

Text #1

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.9479. Min Act: -0.1700

Data Index: 8657283 (Open Web Text)

Max Activating Token Index: 686

Text #2

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.9017. Min Act: -0.1700

Data Index: 3396056 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8715. Min Act: -0.1700

Data Index: 3215219 (Open Web Text)

Max Activating Token Index: 953

Text #4

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8852. Min Act: -0.1700

Data Index: 2603866 (Open Web Text)

Max Activating Token Index: 96

Text #5

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8828. Min Act: -0.1700

Data Index: 3350254 (Open Web Text)

Max Activating Token Index: 897

Text #6

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8705. Min Act: -0.1700

Data Index: 3606968 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8564. Min Act: -0.1700

Data Index: 8773299 (Open Web Text)

Max Activating Token Index: 939

Text #8

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8318. Min Act: -0.1700

Data Index: 1633800 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8478. Min Act: -0.1700

Data Index: 1710959 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8251. Min Act: -0.1700

Data Index: 2824973 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8352. Min Act: -0.1700

Data Index: 6897950 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8063. Min Act: -0.1700

Data Index: 2115716 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8328. Min Act: -0.1700

Data Index: 7246281 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8006. Min Act: -0.1700

Data Index: 4409341 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8171. Min Act: -0.1700

Data Index: 1982482 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8056. Min Act: -0.1700

Data Index: 1965464 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8004. Min Act: -0.1700

Data Index: 969395 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8234. Min Act: -0.1700

Data Index: 620330 (Open Web Text)

Max Activating Token Index: 63

Text #19

Max Range: 4.0586. Min Range: -4.0586

Max Act: 3.8018. Min Act: -0.1700

Data Index: 600502 (Open Web Text)

Max Activating Token Index: 4