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

Dataset: Open Web Text

Neuron 1320 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: 3.0332. Min Range: -3.0332

Max Act: 3.0332. Min Act: -0.1700

Data Index: 6012648 (Open Web Text)

Max Activating Token Index: 1020

Text #1

Max Range: 3.0332. Min Range: -3.0332

Max Act: 3.0266. Min Act: -0.1700

Data Index: 1476844 (Open Web Text)

Max Activating Token Index: 723

Text #2

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9953. Min Act: -0.1700

Data Index: 4861795 (Open Web Text)

Max Activating Token Index: 778

Text #3

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9963. Min Act: -0.1700

Data Index: 1453659 (Open Web Text)

Max Activating Token Index: 639

Text #4

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9756. Min Act: -0.1700

Data Index: 5575356 (Open Web Text)

Max Activating Token Index: 121

Text #5

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9703. Min Act: -0.1700

Data Index: 6557629 (Open Web Text)

Max Activating Token Index: 268

Text #6

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9504. Min Act: -0.1700

Data Index: 5845223 (Open Web Text)

Max Activating Token Index: 307

Text #7

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9344. Min Act: -0.1700

Data Index: 8675526 (Open Web Text)

Max Activating Token Index: 892

Text #8

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9447. Min Act: -0.1700

Data Index: 1545215 (Open Web Text)

Max Activating Token Index: 820

Text #9

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9258. Min Act: -0.1700

Data Index: 1608794 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9222. Min Act: -0.1700

Data Index: 8245732 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9334. Min Act: -0.1700

Data Index: 4167224 (Open Web Text)

Max Activating Token Index: 449

Text #12

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9130. Min Act: -0.1700

Data Index: 1995377 (Open Web Text)

Max Activating Token Index: 652

Text #13

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9088. Min Act: -0.1700

Data Index: 1968767 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.8972. Min Act: -0.1700

Data Index: 4103896 (Open Web Text)

Max Activating Token Index: 453

Text #15

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.8799. Min Act: -0.1700

Data Index: 6768582 (Open Web Text)

Max Activating Token Index: 314

Text #16

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.8919. Min Act: -0.1700

Data Index: 7092385 (Open Web Text)

Max Activating Token Index: 570

Text #17

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.8810. Min Act: -0.1700

Data Index: 5825890 (Open Web Text)

Max Activating Token Index: 945

Text #18

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.8846. Min Act: -0.1700

Data Index: 373568 (Open Web Text)

Max Activating Token Index: 935

Text #19

Max Range: 3.0332. Min Range: -3.0332

Max Act: 2.9019. Min Act: -0.1700

Data Index: 5797428 (Open Web Text)

Max Activating Token Index: 857