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

Dataset: Open Web Text

Neuron 1989 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: 3.6314. Min Range: -3.6314

Max Act: 3.6314. Min Act: -0.1700

Data Index: 969737 (Open Web Text)

Max Activating Token Index: 823

Text #1

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6007. Min Act: -0.1700

Data Index: 5721017 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6118. Min Act: -0.1700

Data Index: 1393814 (Open Web Text)

Max Activating Token Index: 311

Text #3

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6196. Min Act: -0.1700

Data Index: 6772959 (Open Web Text)

Max Activating Token Index: 863

Text #4

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.6068. Min Act: -0.1700

Data Index: 8689765 (Open Web Text)

Max Activating Token Index: 655

Text #5

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5761. Min Act: -0.1700

Data Index: 596635 (Open Web Text)

Max Activating Token Index: 81

Text #6

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5830. Min Act: -0.1700

Data Index: 5935704 (Open Web Text)

Max Activating Token Index: 662

Text #7

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5695. Min Act: -0.1700

Data Index: 205168 (Open Web Text)

Max Activating Token Index: 315

Text #8

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5784. Min Act: -0.1700

Data Index: 1335116 (Open Web Text)

Max Activating Token Index: 668

Text #9

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5932. Min Act: -0.1700

Data Index: 8261920 (Open Web Text)

Max Activating Token Index: 758

Text #10

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5950. Min Act: -0.1700

Data Index: 5849590 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5667. Min Act: -0.1700

Data Index: 6210994 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5638. Min Act: -0.1700

Data Index: 7134878 (Open Web Text)

Max Activating Token Index: 125

Text #13

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5695. Min Act: -0.1700

Data Index: 2577150 (Open Web Text)

Max Activating Token Index: 818

Text #14

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5657. Min Act: -0.1700

Data Index: 636040 (Open Web Text)

Max Activating Token Index: 173

Text #15

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5728. Min Act: -0.1700

Data Index: 429548 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5717. Min Act: -0.1700

Data Index: 6470151 (Open Web Text)

Max Activating Token Index: 583

Text #17

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5553. Min Act: -0.1700

Data Index: 2604291 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5669. Min Act: -0.1700

Data Index: 8810890 (Open Web Text)

Max Activating Token Index: 801

Text #19

Max Range: 3.6314. Min Range: -3.6314

Max Act: 3.5516. Min Act: -0.1700

Data Index: 3955346 (Open Web Text)

Max Activating Token Index: 180