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

Dataset: Open Web Text

Neuron 1520 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: 3.0613. Min Range: -3.0613

Max Act: 3.0613. Min Act: -0.1700

Data Index: 8023364 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0588. Min Act: -0.1700

Data Index: 1300828 (Open Web Text)

Max Activating Token Index: 347

Text #2

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0603. Min Act: -0.1700

Data Index: 3645800 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 3.0613. Min Range: -3.0613

Max Act: 3.0090. Min Act: -0.1700

Data Index: 6669226 (Open Web Text)

Max Activating Token Index: 579

Text #4

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9664. Min Act: -0.1700

Data Index: 1917410 (Open Web Text)

Max Activating Token Index: 63

Text #5

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9664. Min Act: -0.1700

Data Index: 1320720 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9526. Min Act: -0.1700

Data Index: 5531156 (Open Web Text)

Max Activating Token Index: 549

Text #7

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9476. Min Act: -0.1700

Data Index: 1675998 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9376. Min Act: -0.1700

Data Index: 7317349 (Open Web Text)

Max Activating Token Index: 769

Text #9

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9269. Min Act: -0.1700

Data Index: 720930 (Open Web Text)

Max Activating Token Index: 777

Text #10

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9328. Min Act: -0.1700

Data Index: 5682407 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9001. Min Act: -0.1700

Data Index: 5377023 (Open Web Text)

Max Activating Token Index: 807

Text #12

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9026. Min Act: -0.1700

Data Index: 366202 (Open Web Text)

Max Activating Token Index: 383

Text #13

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.8961. Min Act: -0.1700

Data Index: 7211362 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.9045. Min Act: -0.1700

Data Index: 4179567 (Open Web Text)

Max Activating Token Index: 323

Text #15

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.8902. Min Act: -0.1700

Data Index: 5128563 (Open Web Text)

Max Activating Token Index: 251

Text #16

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.8849. Min Act: -0.1700

Data Index: 6916573 (Open Web Text)

Max Activating Token Index: 165

Text #17

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.8877. Min Act: -0.1700

Data Index: 1553727 (Open Web Text)

Max Activating Token Index: 215

Text #18

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.8816. Min Act: -0.1700

Data Index: 4078441 (Open Web Text)

Max Activating Token Index: 193

Text #19

Max Range: 3.0613. Min Range: -3.0613

Max Act: 2.8825. Min Act: -0.1700

Data Index: 5785593 (Open Web Text)

Max Activating Token Index: 102