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

Dataset: Open Web Text

Neuron 1120 in Layer 0

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: 2.7826. Min Range: -2.7826

Max Act: 2.7826. Min Act: -0.1700

Data Index: 4047273 (Open Web Text)

Max Activating Token Index: 863

Text #1

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7779. Min Act: -0.1700

Data Index: 1299664 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7385. Min Act: -0.1700

Data Index: 4813365 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7365. Min Act: -0.1700

Data Index: 5284145 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7229. Min Act: -0.1700

Data Index: 4668139 (Open Web Text)

Max Activating Token Index: 45

Text #5

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7237. Min Act: -0.1700

Data Index: 6322676 (Open Web Text)

Max Activating Token Index: 319

Text #6

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7309. Min Act: -0.1700

Data Index: 2375612 (Open Web Text)

Max Activating Token Index: 756

Text #7

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7253. Min Act: -0.1700

Data Index: 4644651 (Open Web Text)

Max Activating Token Index: 672

Text #8

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.7112. Min Act: -0.1700

Data Index: 8334880 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6889. Min Act: -0.1700

Data Index: 6351249 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6840. Min Act: -0.1700

Data Index: 3165589 (Open Web Text)

Max Activating Token Index: 702

Text #11

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6937. Min Act: -0.1700

Data Index: 7495548 (Open Web Text)

Max Activating Token Index: 285

Text #12

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6924. Min Act: -0.1700

Data Index: 2403356 (Open Web Text)

Max Activating Token Index: 581

Text #13

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6787. Min Act: -0.1700

Data Index: 3308718 (Open Web Text)

Max Activating Token Index: 431

Text #14

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6988. Min Act: -0.1700

Data Index: 6017269 (Open Web Text)

Max Activating Token Index: 89

Text #15

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6674. Min Act: -0.1700

Data Index: 1264893 (Open Web Text)

Max Activating Token Index: 225

Text #16

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6758. Min Act: -0.1700

Data Index: 6157897 (Open Web Text)

Max Activating Token Index: 440

Text #17

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6729. Min Act: -0.1700

Data Index: 4166469 (Open Web Text)

Max Activating Token Index: 759

Text #18

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6823. Min Act: -0.1700

Data Index: 5940422 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 2.7826. Min Range: -2.7826

Max Act: 2.6761. Min Act: -0.1700

Data Index: 5380846 (Open Web Text)

Max Activating Token Index: 7