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

Dataset: Open Web Text

Neuron 970 in Layer 5

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: 3.7010. Min Range: -3.7010

Max Act: 3.7010. Min Act: -0.1700

Data Index: 1840209 (Open Web Text)

Max Activating Token Index: 406

Text #1

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.6207. Min Act: -0.1700

Data Index: 4111341 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.5687. Min Act: -0.1700

Data Index: 6758265 (Open Web Text)

Max Activating Token Index: 663

Text #3

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.5344. Min Act: -0.1700

Data Index: 1840210 (Open Web Text)

Max Activating Token Index: 648

Text #4

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.5540. Min Act: -0.1700

Data Index: 4111337 (Open Web Text)

Max Activating Token Index: 392

Text #5

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.5528. Min Act: -0.1700

Data Index: 1576924 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.5149. Min Act: -0.1700

Data Index: 5169623 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.5333. Min Act: -0.1700

Data Index: 5169621 (Open Web Text)

Max Activating Token Index: 870

Text #8

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4801. Min Act: -0.1700

Data Index: 6317050 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4582. Min Act: -0.1700

Data Index: 6134264 (Open Web Text)

Max Activating Token Index: 484

Text #10

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4541. Min Act: -0.1700

Data Index: 3190641 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4322. Min Act: -0.1700

Data Index: 6594854 (Open Web Text)

Max Activating Token Index: 522

Text #12

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4402. Min Act: -0.1700

Data Index: 4460531 (Open Web Text)

Max Activating Token Index: 699

Text #13

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4319. Min Act: -0.1700

Data Index: 255853 (Open Web Text)

Max Activating Token Index: 869

Text #14

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.3804. Min Act: -0.1700

Data Index: 7270019 (Open Web Text)

Max Activating Token Index: 879

Text #15

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.3952. Min Act: -0.1700

Data Index: 4246526 (Open Web Text)

Max Activating Token Index: 845

Text #16

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.3919. Min Act: -0.1700

Data Index: 7642777 (Open Web Text)

Max Activating Token Index: 814

Text #17

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4001. Min Act: -0.1700

Data Index: 6576364 (Open Web Text)

Max Activating Token Index: 103

Text #18

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4045. Min Act: -0.1700

Data Index: 8761804 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 3.7010. Min Range: -3.7010

Max Act: 3.4043. Min Act: -0.1700

Data Index: 5113555 (Open Web Text)

Max Activating Token Index: 691