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

Dataset: Open Web Text

Neuron 2785 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: 4.4413. Min Range: -4.4413

Max Act: 4.4288. Min Act: -0.1700

Data Index: 3633406 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.4259. Min Act: -0.1700

Data Index: 1668041 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.4281. Min Act: -0.1700

Data Index: 3958021 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.4413. Min Act: -0.1700

Data Index: 8753700 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3897. Min Act: -0.1700

Data Index: 1872914 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.4073. Min Act: -0.1700

Data Index: 2941110 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3875. Min Act: -0.1700

Data Index: 8451450 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3878. Min Act: -0.1700

Data Index: 4846251 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3791. Min Act: -0.1700

Data Index: 1060094 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3538. Min Act: -0.1700

Data Index: 7418615 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3509. Min Act: -0.1700

Data Index: 1058351 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3637. Min Act: -0.1700

Data Index: 6595822 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3603. Min Act: -0.1700

Data Index: 5121483 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3602. Min Act: -0.1700

Data Index: 457713 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3588. Min Act: -0.1700

Data Index: 3702614 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3366. Min Act: -0.1700

Data Index: 5017225 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3269. Min Act: -0.1700

Data Index: 2601055 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3229. Min Act: -0.1700

Data Index: 1453362 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3385. Min Act: -0.1700

Data Index: 2356648 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.4413. Min Range: -4.4413

Max Act: 4.3338. Min Act: -0.1700

Data Index: 4612337 (Open Web Text)

Max Activating Token Index: 4