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

Dataset: Open Web Text

Neuron 1805 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: 6.8417. Min Range: -6.8417

Max Act: 6.8417. Min Act: -0.1700

Data Index: 8473013 (Open Web Text)

Max Activating Token Index: 900

Text #1

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.4503. Min Act: -0.1700

Data Index: 3647159 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.4300. Min Act: -0.1700

Data Index: 7207098 (Open Web Text)

Max Activating Token Index: 622

Text #3

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.4154. Min Act: -0.1700

Data Index: 3687249 (Open Web Text)

Max Activating Token Index: 845

Text #4

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.4444. Min Act: -0.1700

Data Index: 8386841 (Open Web Text)

Max Activating Token Index: 1008

Text #5

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.3157. Min Act: -0.1700

Data Index: 4129670 (Open Web Text)

Max Activating Token Index: 940

Text #6

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.3313. Min Act: -0.1700

Data Index: 1769105 (Open Web Text)

Max Activating Token Index: 924

Text #7

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.2625. Min Act: -0.1700

Data Index: 6307888 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.3003. Min Act: -0.1700

Data Index: 1693980 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.2765. Min Act: -0.1700

Data Index: 4867227 (Open Web Text)

Max Activating Token Index: 690

Text #10

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.2924. Min Act: -0.1700

Data Index: 1083693 (Open Web Text)

Max Activating Token Index: 785

Text #11

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.3203. Min Act: -0.1700

Data Index: 4742089 (Open Web Text)

Max Activating Token Index: 625

Text #12

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.1875. Min Act: -0.1700

Data Index: 7143756 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.2600. Min Act: -0.1700

Data Index: 1934644 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.1905. Min Act: -0.1700

Data Index: 7715553 (Open Web Text)

Max Activating Token Index: 738

Text #15

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.1654. Min Act: -0.1700

Data Index: 3162452 (Open Web Text)

Max Activating Token Index: 249

Text #16

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.1709. Min Act: -0.1700

Data Index: 5559717 (Open Web Text)

Max Activating Token Index: 939

Text #17

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.1405. Min Act: -0.1700

Data Index: 6332837 (Open Web Text)

Max Activating Token Index: 987

Text #18

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.2130. Min Act: -0.1700

Data Index: 2235340 (Open Web Text)

Max Activating Token Index: 927

Text #19

Max Range: 6.8417. Min Range: -6.8417

Max Act: 6.1966. Min Act: -0.1700

Data Index: 4804747 (Open Web Text)

Max Activating Token Index: 732