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

Dataset: Open Web Text

Neuron 916 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: 6.1797. Min Range: -6.1797

Max Act: 6.1797. Min Act: -0.1700

Data Index: 1075739 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.1479. Min Act: -0.1700

Data Index: 3892929 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.1442. Min Act: -0.1700

Data Index: 6779563 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.1362. Min Act: -0.1700

Data Index: 5938439 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0965. Min Act: -0.1700

Data Index: 7542875 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0887. Min Act: -0.1700

Data Index: 7321005 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0628. Min Act: -0.1700

Data Index: 4702752 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0570. Min Act: -0.1700

Data Index: 2278660 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0852. Min Act: -0.1700

Data Index: 2900476 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0349. Min Act: -0.1700

Data Index: 6921655 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0415. Min Act: -0.1700

Data Index: 8463097 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0421. Min Act: -0.1700

Data Index: 3075968 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0292. Min Act: -0.1700

Data Index: 1647603 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0415. Min Act: -0.1700

Data Index: 859395 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0415. Min Act: -0.1700

Data Index: 11305 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0192. Min Act: -0.1700

Data Index: 1010740 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0264. Min Act: -0.1700

Data Index: 2224901 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0415. Min Act: -0.1700

Data Index: 4283386 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0415. Min Act: -0.1700

Data Index: 3426298 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 6.1797. Min Range: -6.1797

Max Act: 6.0415. Min Act: -0.1700

Data Index: 6622757 (Open Web Text)

Max Activating Token Index: 3