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

Dataset: Open Web Text

Neuron 1353 in Layer 4

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: 3.6838. Min Range: -3.6838

Max Act: 3.6789. Min Act: -0.1700

Data Index: 4018241 (Open Web Text)

Max Activating Token Index: 392

Text #1

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.6838. Min Act: -0.1700

Data Index: 6977502 (Open Web Text)

Max Activating Token Index: 742

Text #2

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5910. Min Act: -0.1700

Data Index: 3998455 (Open Web Text)

Max Activating Token Index: 383

Text #3

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5514. Min Act: -0.1700

Data Index: 1443943 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.5060. Min Act: -0.1700

Data Index: 8059743 (Open Web Text)

Max Activating Token Index: 973

Text #5

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4763. Min Act: -0.1700

Data Index: 5927837 (Open Web Text)

Max Activating Token Index: 571

Text #6

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4851. Min Act: -0.1700

Data Index: 8711065 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4994. Min Act: -0.1700

Data Index: 6254875 (Open Web Text)

Max Activating Token Index: 229

Text #8

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4731. Min Act: -0.1700

Data Index: 7143225 (Open Web Text)

Max Activating Token Index: 155

Text #9

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4818. Min Act: -0.1700

Data Index: 5637748 (Open Web Text)

Max Activating Token Index: 582

Text #10

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4678. Min Act: -0.1700

Data Index: 5387611 (Open Web Text)

Max Activating Token Index: 1007

Text #11

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4574. Min Act: -0.1700

Data Index: 3855503 (Open Web Text)

Max Activating Token Index: 901

Text #12

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4718. Min Act: -0.1700

Data Index: 898221 (Open Web Text)

Max Activating Token Index: 861

Text #13

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4437. Min Act: -0.1700

Data Index: 8784630 (Open Web Text)

Max Activating Token Index: 679

Text #14

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4353. Min Act: -0.1700

Data Index: 8624421 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4488. Min Act: -0.1700

Data Index: 8044454 (Open Web Text)

Max Activating Token Index: 303

Text #16

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1305615 (Open Web Text)

Max Activating Token Index: 853

Text #17

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4292. Min Act: -0.1700

Data Index: 8360170 (Open Web Text)

Max Activating Token Index: 908

Text #18

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4216. Min Act: -0.1700

Data Index: 5025851 (Open Web Text)

Max Activating Token Index: 433

Text #19

Max Range: 3.6838. Min Range: -3.6838

Max Act: 3.4154. Min Act: -0.1700

Data Index: 78099 (Open Web Text)

Max Activating Token Index: 650