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

Dataset: Open Web Text

Neuron 315 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: 3.8677. Min Range: -3.8677

Max Act: 3.8677. Min Act: -0.1700

Data Index: 5633386 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.8402. Min Act: -0.1700

Data Index: 8544999 (Open Web Text)

Max Activating Token Index: 272

Text #2

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.8016. Min Act: -0.1700

Data Index: 3848095 (Open Web Text)

Max Activating Token Index: 829

Text #3

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.8210. Min Act: -0.1700

Data Index: 8179983 (Open Web Text)

Max Activating Token Index: 931

Text #4

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.8247. Min Act: -0.1700

Data Index: 369938 (Open Web Text)

Max Activating Token Index: 455

Text #5

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7849. Min Act: -0.1700

Data Index: 8196970 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.8045. Min Act: -0.1700

Data Index: 8368454 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7809. Min Act: -0.1700

Data Index: 4976640 (Open Web Text)

Max Activating Token Index: 638

Text #8

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7808. Min Act: -0.1700

Data Index: 6399466 (Open Web Text)

Max Activating Token Index: 451

Text #9

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7783. Min Act: -0.1700

Data Index: 2298902 (Open Web Text)

Max Activating Token Index: 1009

Text #10

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7728. Min Act: -0.1700

Data Index: 3415613 (Open Web Text)

Max Activating Token Index: 288

Text #11

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7652. Min Act: -0.1700

Data Index: 4623181 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7941. Min Act: -0.1700

Data Index: 756952 (Open Web Text)

Max Activating Token Index: 759

Text #13

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7218. Min Act: -0.1700

Data Index: 5564642 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7672. Min Act: -0.1700

Data Index: 4583569 (Open Web Text)

Max Activating Token Index: 493

Text #15

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7324. Min Act: -0.1700

Data Index: 3600069 (Open Web Text)

Max Activating Token Index: 56

Text #16

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7573. Min Act: -0.1700

Data Index: 5612039 (Open Web Text)

Max Activating Token Index: 590

Text #17

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7487. Min Act: -0.1700

Data Index: 6471831 (Open Web Text)

Max Activating Token Index: 668

Text #18

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7394. Min Act: -0.1700

Data Index: 5220188 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.7265. Min Act: -0.1700

Data Index: 5175435 (Open Web Text)

Max Activating Token Index: 947