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

Dataset: Open Web Text

Neuron 2790 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: 3.9732. Min Range: -3.9732

Max Act: 3.9732. Min Act: -0.1700

Data Index: 7373652 (Open Web Text)

Max Activating Token Index: 522

Text #1

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.8317. Min Act: -0.1700

Data Index: 8111247 (Open Web Text)

Max Activating Token Index: 1022

Text #2

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.8284. Min Act: -0.1700

Data Index: 8475026 (Open Web Text)

Max Activating Token Index: 302

Text #3

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7943. Min Act: -0.1700

Data Index: 3344113 (Open Web Text)

Max Activating Token Index: 617

Text #4

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7974. Min Act: -0.1700

Data Index: 4561886 (Open Web Text)

Max Activating Token Index: 978

Text #5

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.8057. Min Act: -0.1700

Data Index: 3313847 (Open Web Text)

Max Activating Token Index: 312

Text #6

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7756. Min Act: -0.1700

Data Index: 7731163 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7801. Min Act: -0.1700

Data Index: 8789673 (Open Web Text)

Max Activating Token Index: 749

Text #8

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7424. Min Act: -0.1700

Data Index: 3073572 (Open Web Text)

Max Activating Token Index: 261

Text #9

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7167. Min Act: -0.1700

Data Index: 5180704 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6895. Min Act: -0.1700

Data Index: 1434327 (Open Web Text)

Max Activating Token Index: 87

Text #11

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7120. Min Act: -0.1700

Data Index: 7510421 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.7129. Min Act: -0.1700

Data Index: 128582 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6701. Min Act: -0.1700

Data Index: 5919390 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6916. Min Act: -0.1700

Data Index: 8668448 (Open Web Text)

Max Activating Token Index: 87

Text #15

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6925. Min Act: -0.1700

Data Index: 4314696 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6639. Min Act: -0.1700

Data Index: 1965271 (Open Web Text)

Max Activating Token Index: 361

Text #17

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6506. Min Act: -0.1700

Data Index: 5398900 (Open Web Text)

Max Activating Token Index: 759

Text #18

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6520. Min Act: -0.1700

Data Index: 675597 (Open Web Text)

Max Activating Token Index: 768

Text #19

Max Range: 3.9732. Min Range: -3.9732

Max Act: 3.6469. Min Act: -0.1700

Data Index: 8234873 (Open Web Text)

Max Activating Token Index: 197