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

Dataset: Open Web Text

Neuron 1354 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: 4.0056. Min Range: -4.0056

Max Act: 4.0056. Min Act: -0.1700

Data Index: 2979637 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.9222. Min Act: -0.1700

Data Index: 4406011 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.9035. Min Act: -0.1700

Data Index: 7850860 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8852. Min Act: -0.1700

Data Index: 1446927 (Open Web Text)

Max Activating Token Index: 352

Text #4

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.9062. Min Act: -0.1700

Data Index: 3825071 (Open Web Text)

Max Activating Token Index: 320

Text #5

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8336. Min Act: -0.1700

Data Index: 4896101 (Open Web Text)

Max Activating Token Index: 274

Text #6

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8350. Min Act: -0.1700

Data Index: 8038612 (Open Web Text)

Max Activating Token Index: 733

Text #7

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8512. Min Act: -0.1700

Data Index: 365094 (Open Web Text)

Max Activating Token Index: 421

Text #8

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8236. Min Act: -0.1700

Data Index: 7361915 (Open Web Text)

Max Activating Token Index: 339

Text #9

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8373. Min Act: -0.1700

Data Index: 5835490 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8319. Min Act: -0.1700

Data Index: 1921000 (Open Web Text)

Max Activating Token Index: 191

Text #11

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8440. Min Act: -0.1700

Data Index: 8820171 (Open Web Text)

Max Activating Token Index: 872

Text #12

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8530. Min Act: -0.1700

Data Index: 25356 (Open Web Text)

Max Activating Token Index: 689

Text #13

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8232. Min Act: -0.1700

Data Index: 3641365 (Open Web Text)

Max Activating Token Index: 661

Text #14

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8050. Min Act: -0.1700

Data Index: 3025653 (Open Web Text)

Max Activating Token Index: 833

Text #15

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.7907. Min Act: -0.1700

Data Index: 5190939 (Open Web Text)

Max Activating Token Index: 908

Text #16

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.7937. Min Act: -0.1700

Data Index: 4197811 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.8121. Min Act: -0.1700

Data Index: 4436850 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.7992. Min Act: -0.1700

Data Index: 5002515 (Open Web Text)

Max Activating Token Index: 928

Text #19

Max Range: 4.0056. Min Range: -4.0056

Max Act: 3.7980. Min Act: -0.1700

Data Index: 7875918 (Open Web Text)

Max Activating Token Index: 670