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

Dataset: Open Web Text

Neuron 2331 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: 3.3718. Min Range: -3.3718

Max Act: 3.3718. Min Act: -0.1700

Data Index: 5263500 (Open Web Text)

Max Activating Token Index: 745

Text #1

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.1766. Min Act: -0.1700

Data Index: 1661935 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.1510. Min Act: -0.1700

Data Index: 4145217 (Open Web Text)

Max Activating Token Index: 353

Text #3

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.1267. Min Act: -0.1700

Data Index: 2722953 (Open Web Text)

Max Activating Token Index: 407

Text #4

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.0174. Min Act: -0.1700

Data Index: 3529330 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.0069. Min Act: -0.1700

Data Index: 100559 (Open Web Text)

Max Activating Token Index: 201

Text #6

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.0288. Min Act: -0.1700

Data Index: 3423955 (Open Web Text)

Max Activating Token Index: 409

Text #7

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9938. Min Act: -0.1700

Data Index: 4561673 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 3.3718. Min Range: -3.3718

Max Act: 3.0204. Min Act: -0.1700

Data Index: 7520904 (Open Web Text)

Max Activating Token Index: 163

Text #9

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9796. Min Act: -0.1700

Data Index: 6778788 (Open Web Text)

Max Activating Token Index: 809

Text #10

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9663. Min Act: -0.1700

Data Index: 7654987 (Open Web Text)

Max Activating Token Index: 127

Text #11

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9641. Min Act: -0.1700

Data Index: 851831 (Open Web Text)

Max Activating Token Index: 894

Text #12

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9646. Min Act: -0.1700

Data Index: 1119703 (Open Web Text)

Max Activating Token Index: 777

Text #13

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9667. Min Act: -0.1700

Data Index: 2432435 (Open Web Text)

Max Activating Token Index: 537

Text #14

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9508. Min Act: -0.1700

Data Index: 6120275 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9599. Min Act: -0.1700

Data Index: 2877977 (Open Web Text)

Max Activating Token Index: 834

Text #16

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9504. Min Act: -0.1700

Data Index: 7063037 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9501. Min Act: -0.1700

Data Index: 5032827 (Open Web Text)

Max Activating Token Index: 362

Text #18

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9441. Min Act: -0.1700

Data Index: 126314 (Open Web Text)

Max Activating Token Index: 988

Text #19

Max Range: 3.3718. Min Range: -3.3718

Max Act: 2.9391. Min Act: -0.1700

Data Index: 5780691 (Open Web Text)

Max Activating Token Index: 870