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

Dataset: Open Web Text

Neuron 775 in Layer 1

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: 3.8768. Min Range: -3.8768

Max Act: 3.8768. Min Act: -0.1700

Data Index: 4415557 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8522. Min Act: -0.1700

Data Index: 4849054 (Open Web Text)

Max Activating Token Index: 662

Text #2

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8553. Min Act: -0.1700

Data Index: 2906397 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8160. Min Act: -0.1700

Data Index: 2094340 (Open Web Text)

Max Activating Token Index: 521

Text #4

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8194. Min Act: -0.1700

Data Index: 4923831 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8192. Min Act: -0.1700

Data Index: 8753027 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8106. Min Act: -0.1700

Data Index: 5737259 (Open Web Text)

Max Activating Token Index: 645

Text #7

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8144. Min Act: -0.1700

Data Index: 5894990 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8225. Min Act: -0.1700

Data Index: 1537099 (Open Web Text)

Max Activating Token Index: 554

Text #9

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.8223. Min Act: -0.1700

Data Index: 6545774 (Open Web Text)

Max Activating Token Index: 475

Text #10

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7914. Min Act: -0.1700

Data Index: 6285076 (Open Web Text)

Max Activating Token Index: 106

Text #11

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7751. Min Act: -0.1700

Data Index: 4277255 (Open Web Text)

Max Activating Token Index: 702

Text #12

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1894479 (Open Web Text)

Max Activating Token Index: 202

Text #13

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7857. Min Act: -0.1700

Data Index: 8607029 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7952. Min Act: -0.1700

Data Index: 8591510 (Open Web Text)

Max Activating Token Index: 526

Text #15

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7781. Min Act: -0.1700

Data Index: 7384413 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7822. Min Act: -0.1700

Data Index: 5148544 (Open Web Text)

Max Activating Token Index: 466

Text #17

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7871. Min Act: -0.1700

Data Index: 614501 (Open Web Text)

Max Activating Token Index: 560

Text #18

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7938. Min Act: -0.1700

Data Index: 1222964 (Open Web Text)

Max Activating Token Index: 538

Text #19

Max Range: 3.8768. Min Range: -3.8768

Max Act: 3.7703. Min Act: -0.1700

Data Index: 1994600 (Open Web Text)

Max Activating Token Index: 609