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

Dataset: Open Web Text

Neuron 1323 in Layer 2

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: 1.9439. Min Range: -1.9439

Max Act: 1.9438. Min Act: -0.1700

Data Index: 5821088 (Open Web Text)

Max Activating Token Index: 245

Text #1

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.9417. Min Act: -0.1700

Data Index: 5729466 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.9366. Min Act: -0.1700

Data Index: 3993774 (Open Web Text)

Max Activating Token Index: 497

Text #3

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.9439. Min Act: -0.1700

Data Index: 4327702 (Open Web Text)

Max Activating Token Index: 453

Text #4

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.9079. Min Act: -0.1700

Data Index: 1175090 (Open Web Text)

Max Activating Token Index: 988

Text #5

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.9223. Min Act: -0.1700

Data Index: 874379 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.9131. Min Act: -0.1700

Data Index: 4073983 (Open Web Text)

Max Activating Token Index: 657

Text #7

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8959. Min Act: -0.1700

Data Index: 8013077 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.9070. Min Act: -0.1700

Data Index: 6509412 (Open Web Text)

Max Activating Token Index: 552

Text #9

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8969. Min Act: -0.1700

Data Index: 1524686 (Open Web Text)

Max Activating Token Index: 239

Text #10

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8799. Min Act: -0.1700

Data Index: 5108428 (Open Web Text)

Max Activating Token Index: 870

Text #11

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8642. Min Act: -0.1700

Data Index: 8006919 (Open Web Text)

Max Activating Token Index: 705

Text #12

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8758. Min Act: -0.1700

Data Index: 409260 (Open Web Text)

Max Activating Token Index: 759

Text #13

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8733. Min Act: -0.1700

Data Index: 5287724 (Open Web Text)

Max Activating Token Index: 922

Text #14

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8822. Min Act: -0.1700

Data Index: 7626766 (Open Web Text)

Max Activating Token Index: 249

Text #15

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8715. Min Act: -0.1700

Data Index: 5933196 (Open Web Text)

Max Activating Token Index: 858

Text #16

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8670. Min Act: -0.1700

Data Index: 8221860 (Open Web Text)

Max Activating Token Index: 831

Text #17

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8746. Min Act: -0.1700

Data Index: 1668934 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8837. Min Act: -0.1700

Data Index: 2110471 (Open Web Text)

Max Activating Token Index: 465

Text #19

Max Range: 1.9439. Min Range: -1.9439

Max Act: 1.8695. Min Act: -0.1700

Data Index: 7871073 (Open Web Text)

Max Activating Token Index: 193