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

Dataset: Open Web Text

Neuron 660 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: 3.8486. Min Range: -3.8486

Max Act: 3.8486. Min Act: -0.1700

Data Index: 7341083 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.8481. Min Act: -0.1700

Data Index: 1758644 (Open Web Text)

Max Activating Token Index: 611

Text #2

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.8201. Min Act: -0.1700

Data Index: 4655622 (Open Web Text)

Max Activating Token Index: 927

Text #3

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7989. Min Act: -0.1700

Data Index: 681273 (Open Web Text)

Max Activating Token Index: 302

Text #4

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7817. Min Act: -0.1700

Data Index: 3144434 (Open Web Text)

Max Activating Token Index: 861

Text #5

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7831. Min Act: -0.1700

Data Index: 892757 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7708. Min Act: -0.1700

Data Index: 3177415 (Open Web Text)

Max Activating Token Index: 478

Text #7

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7656. Min Act: -0.1700

Data Index: 1746459 (Open Web Text)

Max Activating Token Index: 613

Text #8

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7437. Min Act: -0.1700

Data Index: 6598879 (Open Web Text)

Max Activating Token Index: 428

Text #9

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7533. Min Act: -0.1700

Data Index: 8094577 (Open Web Text)

Max Activating Token Index: 29

Text #10

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7443. Min Act: -0.1700

Data Index: 1758649 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7229. Min Act: -0.1700

Data Index: 3396049 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7510. Min Act: -0.1700

Data Index: 2701718 (Open Web Text)

Max Activating Token Index: 718

Text #13

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7431. Min Act: -0.1700

Data Index: 914332 (Open Web Text)

Max Activating Token Index: 178

Text #14

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7329. Min Act: -0.1700

Data Index: 129304 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7136. Min Act: -0.1700

Data Index: 1621235 (Open Web Text)

Max Activating Token Index: 368

Text #16

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7217. Min Act: -0.1700

Data Index: 1774193 (Open Web Text)

Max Activating Token Index: 707

Text #17

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7243. Min Act: -0.1700

Data Index: 129305 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.7142. Min Act: -0.1700

Data Index: 7843722 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 3.8486. Min Range: -3.8486

Max Act: 3.6869. Min Act: -0.1700

Data Index: 3672729 (Open Web Text)

Max Activating Token Index: 117