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

Dataset: Open Web Text

Neuron 2211 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: 5.9430. Min Range: -5.9430

Max Act: 5.9430. Min Act: -0.1700

Data Index: 6272765 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8220. Min Act: -0.1700

Data Index: 4315677 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8355. Min Act: -0.1700

Data Index: 1240342 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8220. Min Act: -0.1700

Data Index: 3468654 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8220. Min Act: -0.1700

Data Index: 7055554 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.8220. Min Act: -0.1700

Data Index: 1015190 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7730. Min Act: -0.1700

Data Index: 2870789 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7804. Min Act: -0.1700

Data Index: 8832681 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7454. Min Act: -0.1700

Data Index: 2502245 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.7082. Min Act: -0.1700

Data Index: 1933114 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6473. Min Act: -0.1700

Data Index: 5220866 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6292. Min Act: -0.1700

Data Index: 8041321 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6292. Min Act: -0.1700

Data Index: 3919838 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6473. Min Act: -0.1700

Data Index: 8217655 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6147. Min Act: -0.1700

Data Index: 1524620 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.6019. Min Act: -0.1700

Data Index: 8413363 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.5929. Min Act: -0.1700

Data Index: 8754402 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.5814. Min Act: -0.1700

Data Index: 3292912 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.5876. Min Act: -0.1699

Data Index: 6173559 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 5.9430. Min Range: -5.9430

Max Act: 5.5809. Min Act: -0.1700

Data Index: 6673496 (Open Web Text)

Max Activating Token Index: 5