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

Dataset: Open Web Text

Neuron 1586 in Layer 6

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: 5.7104. Min Range: -5.7104

Max Act: 5.7104. Min Act: -0.1699

Data Index: 349790 (Open Web Text)

Max Activating Token Index: 981

Text #1

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.4961. Min Act: -0.1700

Data Index: 1323843 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.4305. Min Act: -0.1700

Data Index: 3690871 (Open Web Text)

Max Activating Token Index: 710

Text #3

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3910. Min Act: -0.1697

Data Index: 893996 (Open Web Text)

Max Activating Token Index: 475

Text #4

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3569. Min Act: -0.1700

Data Index: 1922370 (Open Web Text)

Max Activating Token Index: 403

Text #5

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.4075. Min Act: -0.1700

Data Index: 8355838 (Open Web Text)

Max Activating Token Index: 951

Text #6

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3402. Min Act: -0.1700

Data Index: 4328768 (Open Web Text)

Max Activating Token Index: 557

Text #7

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3436. Min Act: -0.1700

Data Index: 6429054 (Open Web Text)

Max Activating Token Index: 854

Text #8

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3372. Min Act: -0.1700

Data Index: 804697 (Open Web Text)

Max Activating Token Index: 859

Text #9

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3253. Min Act: -0.1693

Data Index: 5001076 (Open Web Text)

Max Activating Token Index: 836

Text #10

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3558. Min Act: -0.1700

Data Index: 853061 (Open Web Text)

Max Activating Token Index: 346

Text #11

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3375. Min Act: -0.1700

Data Index: 4116455 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3369. Min Act: -0.1699

Data Index: 1003138 (Open Web Text)

Max Activating Token Index: 511

Text #13

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3170. Min Act: -0.1700

Data Index: 3398279 (Open Web Text)

Max Activating Token Index: 542

Text #14

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3089. Min Act: -0.1700

Data Index: 7791065 (Open Web Text)

Max Activating Token Index: 952

Text #15

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3233. Min Act: -0.1700

Data Index: 8551042 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.3032. Min Act: -0.1699

Data Index: 8399948 (Open Web Text)

Max Activating Token Index: 742

Text #17

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.2819. Min Act: -0.1699

Data Index: 1472746 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.2371. Min Act: -0.1700

Data Index: 7219243 (Open Web Text)

Max Activating Token Index: 195

Text #19

Max Range: 5.7104. Min Range: -5.7104

Max Act: 5.2813. Min Act: -0.1700

Data Index: 6760726 (Open Web Text)

Max Activating Token Index: 629