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

Dataset: Open Web Text

Neuron 1441 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: 4.4881. Min Range: -4.4881

Max Act: 4.4881. Min Act: -0.1700

Data Index: 5422448 (Open Web Text)

Max Activating Token Index: 915

Text #1

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.4849. Min Act: -0.1700

Data Index: 5182418 (Open Web Text)

Max Activating Token Index: 768

Text #2

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.4521. Min Act: -0.1700

Data Index: 3273611 (Open Web Text)

Max Activating Token Index: 575

Text #3

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.4144. Min Act: -0.1700

Data Index: 5209328 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.3191. Min Act: -0.1700

Data Index: 8234929 (Open Web Text)

Max Activating Token Index: 709

Text #5

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.3659. Min Act: -0.1700

Data Index: 4377230 (Open Web Text)

Max Activating Token Index: 332

Text #6

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.3587. Min Act: -0.1700

Data Index: 886787 (Open Web Text)

Max Activating Token Index: 933

Text #7

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.3198. Min Act: -0.1700

Data Index: 5211501 (Open Web Text)

Max Activating Token Index: 151

Text #8

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.3050. Min Act: -0.1700

Data Index: 8604872 (Open Web Text)

Max Activating Token Index: 219

Text #9

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2834. Min Act: -0.1700

Data Index: 4284784 (Open Web Text)

Max Activating Token Index: 750

Text #10

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2720. Min Act: -0.1700

Data Index: 485433 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.3102. Min Act: -0.1700

Data Index: 1920292 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2743. Min Act: -0.1700

Data Index: 2939121 (Open Web Text)

Max Activating Token Index: 904

Text #13

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.3245. Min Act: -0.1700

Data Index: 1323999 (Open Web Text)

Max Activating Token Index: 614

Text #14

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2785. Min Act: -0.1700

Data Index: 1919215 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2594. Min Act: -0.1700

Data Index: 5389615 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2396. Min Act: -0.1700

Data Index: 3250675 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2324. Min Act: -0.1700

Data Index: 6559448 (Open Web Text)

Max Activating Token Index: 670

Text #18

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2409. Min Act: -0.1700

Data Index: 5098957 (Open Web Text)

Max Activating Token Index: 894

Text #19

Max Range: 4.4881. Min Range: -4.4881

Max Act: 4.2411. Min Act: -0.1700

Data Index: 7155662 (Open Web Text)

Max Activating Token Index: 244