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

Dataset: Open Web Text

Neuron 512 in Layer 6

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: 3.0185. Min Range: -3.0185

Max Act: 3.0185. Min Act: -0.1700

Data Index: 833309 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.9704. Min Act: -0.1700

Data Index: 6765284 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.8769. Min Act: -0.1700

Data Index: 8006222 (Open Web Text)

Max Activating Token Index: 530

Text #3

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.8478. Min Act: -0.1700

Data Index: 5717237 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.8542. Min Act: -0.1700

Data Index: 515614 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.8436. Min Act: -0.1700

Data Index: 8755941 (Open Web Text)

Max Activating Token Index: 620

Text #6

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.8339. Min Act: -0.1700

Data Index: 592829 (Open Web Text)

Max Activating Token Index: 683

Text #7

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7763. Min Act: -0.1700

Data Index: 1510841 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7543. Min Act: -0.1700

Data Index: 2289777 (Open Web Text)

Max Activating Token Index: 218

Text #9

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7441. Min Act: -0.1700

Data Index: 3476210 (Open Web Text)

Max Activating Token Index: 719

Text #10

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7408. Min Act: -0.1700

Data Index: 7520022 (Open Web Text)

Max Activating Token Index: 683

Text #11

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7013. Min Act: -0.1700

Data Index: 2482635 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7385. Min Act: -0.1700

Data Index: 5970026 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7304. Min Act: -0.1700

Data Index: 4703462 (Open Web Text)

Max Activating Token Index: 913

Text #14

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7227. Min Act: -0.1700

Data Index: 3839582 (Open Web Text)

Max Activating Token Index: 502

Text #15

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7362. Min Act: -0.1700

Data Index: 554112 (Open Web Text)

Max Activating Token Index: 593

Text #16

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7235. Min Act: -0.1700

Data Index: 1760788 (Open Web Text)

Max Activating Token Index: 590

Text #17

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7300. Min Act: -0.1700

Data Index: 4307266 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7102. Min Act: -0.1700

Data Index: 4374661 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 3.0185. Min Range: -3.0185

Max Act: 2.7021. Min Act: -0.1700

Data Index: 6516538 (Open Web Text)

Max Activating Token Index: 727