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

Dataset: Open Web Text

Neuron 992 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: 3.6669. Min Range: -3.6669

Max Act: 3.6669. Min Act: -0.1700

Data Index: 5864625 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.6433. Min Act: -0.1700

Data Index: 6039916 (Open Web Text)

Max Activating Token Index: 865

Text #2

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.6293. Min Act: -0.1700

Data Index: 6212753 (Open Web Text)

Max Activating Token Index: 928

Text #3

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.6418. Min Act: -0.1700

Data Index: 1092540 (Open Web Text)

Max Activating Token Index: 90

Text #4

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.6101. Min Act: -0.1700

Data Index: 463592 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5936. Min Act: -0.1700

Data Index: 6824490 (Open Web Text)

Max Activating Token Index: 629

Text #6

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5833. Min Act: -0.1700

Data Index: 6744801 (Open Web Text)

Max Activating Token Index: 618

Text #7

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5628. Min Act: -0.1700

Data Index: 8680267 (Open Web Text)

Max Activating Token Index: 753

Text #8

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5862. Min Act: -0.1700

Data Index: 8700764 (Open Web Text)

Max Activating Token Index: 388

Text #9

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5687. Min Act: -0.1700

Data Index: 3501914 (Open Web Text)

Max Activating Token Index: 1006

Text #10

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5684. Min Act: -0.1700

Data Index: 3562158 (Open Web Text)

Max Activating Token Index: 365

Text #11

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5558. Min Act: -0.1700

Data Index: 3234102 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5655. Min Act: -0.1700

Data Index: 6137921 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5472. Min Act: -0.1700

Data Index: 7134753 (Open Web Text)

Max Activating Token Index: 628

Text #14

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5295. Min Act: -0.1700

Data Index: 5437906 (Open Web Text)

Max Activating Token Index: 983

Text #15

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5141. Min Act: -0.1700

Data Index: 1903126 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5195. Min Act: -0.1700

Data Index: 6284769 (Open Web Text)

Max Activating Token Index: 499

Text #17

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5225. Min Act: -0.1700

Data Index: 8494813 (Open Web Text)

Max Activating Token Index: 388

Text #18

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.5208. Min Act: -0.1700

Data Index: 2374898 (Open Web Text)

Max Activating Token Index: 602

Text #19

Max Range: 3.6669. Min Range: -3.6669

Max Act: 3.4957. Min Act: -0.1700

Data Index: 6834609 (Open Web Text)

Max Activating Token Index: 923