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

Dataset: Open Web Text

Neuron 2838 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: 4.0373. Min Range: -4.0373

Max Act: 4.0373. Min Act: -0.1700

Data Index: 5313022 (Open Web Text)

Max Activating Token Index: 400

Text #1

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.8896. Min Act: -0.1700

Data Index: 577075 (Open Web Text)

Max Activating Token Index: 949

Text #2

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.8328. Min Act: -0.1700

Data Index: 8829964 (Open Web Text)

Max Activating Token Index: 541

Text #3

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.8191. Min Act: -0.1700

Data Index: 8094332 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7767. Min Act: -0.1700

Data Index: 2445884 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7904. Min Act: -0.1700

Data Index: 702768 (Open Web Text)

Max Activating Token Index: 623

Text #6

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7872. Min Act: -0.1700

Data Index: 3153932 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7788. Min Act: -0.1700

Data Index: 3120639 (Open Web Text)

Max Activating Token Index: 197

Text #8

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7859. Min Act: -0.1700

Data Index: 6011101 (Open Web Text)

Max Activating Token Index: 222

Text #9

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7917. Min Act: -0.1700

Data Index: 1448376 (Open Web Text)

Max Activating Token Index: 803

Text #10

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7412. Min Act: -0.1700

Data Index: 4084770 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7373. Min Act: -0.1700

Data Index: 6031786 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7362. Min Act: -0.1700

Data Index: 3488007 (Open Web Text)

Max Activating Token Index: 492

Text #13

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7232. Min Act: -0.1700

Data Index: 2145234 (Open Web Text)

Max Activating Token Index: 740

Text #14

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.7001. Min Act: -0.1700

Data Index: 3120637 (Open Web Text)

Max Activating Token Index: 186

Text #15

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.6665. Min Act: -0.1700

Data Index: 2878062 (Open Web Text)

Max Activating Token Index: 908

Text #16

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.6495. Min Act: -0.1700

Data Index: 6011100 (Open Web Text)

Max Activating Token Index: 987

Text #17

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.6789. Min Act: -0.1700

Data Index: 7154289 (Open Web Text)

Max Activating Token Index: 772

Text #18

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.6686. Min Act: -0.1700

Data Index: 2665519 (Open Web Text)

Max Activating Token Index: 174

Text #19

Max Range: 4.0373. Min Range: -4.0373

Max Act: 3.6908. Min Act: -0.1700

Data Index: 7416007 (Open Web Text)

Max Activating Token Index: 747