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

Dataset: Open Web Text

Neuron 2259 in Layer 4

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: 2.7528. Min Range: -2.7528

Max Act: 2.7088. Min Act: -0.1700

Data Index: 7577028 (Open Web Text)

Max Activating Token Index: 566

Text #1

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.7528. Min Act: -0.1700

Data Index: 2731924 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.7228. Min Act: -0.1700

Data Index: 6220375 (Open Web Text)

Max Activating Token Index: 917

Text #3

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.7323. Min Act: -0.1700

Data Index: 8579462 (Open Web Text)

Max Activating Token Index: 449

Text #4

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5811. Min Act: -0.1700

Data Index: 4655322 (Open Web Text)

Max Activating Token Index: 823

Text #5

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5687. Min Act: -0.1700

Data Index: 5607842 (Open Web Text)

Max Activating Token Index: 954

Text #6

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5287. Min Act: -0.1700

Data Index: 5327324 (Open Web Text)

Max Activating Token Index: 665

Text #7

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5528. Min Act: -0.1700

Data Index: 5127804 (Open Web Text)

Max Activating Token Index: 771

Text #8

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5386. Min Act: -0.1700

Data Index: 1926826 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.5510. Min Act: -0.1700

Data Index: 8772931 (Open Web Text)

Max Activating Token Index: 637

Text #10

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4776. Min Act: -0.1700

Data Index: 3609107 (Open Web Text)

Max Activating Token Index: 59

Text #11

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4833. Min Act: -0.1700

Data Index: 7533391 (Open Web Text)

Max Activating Token Index: 654

Text #12

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4179. Min Act: -0.1700

Data Index: 6954857 (Open Web Text)

Max Activating Token Index: 417

Text #13

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4254. Min Act: -0.1700

Data Index: 1811830 (Open Web Text)

Max Activating Token Index: 613

Text #14

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4620. Min Act: -0.1700

Data Index: 2626072 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4297. Min Act: -0.1700

Data Index: 5492664 (Open Web Text)

Max Activating Token Index: 54

Text #16

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.3853. Min Act: -0.1700

Data Index: 6453548 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.4394. Min Act: -0.1700

Data Index: 765003 (Open Web Text)

Max Activating Token Index: 678

Text #18

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.3510. Min Act: -0.1700

Data Index: 5908249 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 2.7528. Min Range: -2.7528

Max Act: 2.3857. Min Act: -0.1700

Data Index: 5131858 (Open Web Text)

Max Activating Token Index: 449