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

Dataset: Open Web Text

Neuron 2541 in Layer 0

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: 3.6672. Min Range: -3.6672

Max Act: 3.6672. Min Act: -0.1700

Data Index: 4549942 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.6624. Min Act: -0.1700

Data Index: 7131511 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.6272. Min Act: -0.1700

Data Index: 8717772 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.6112. Min Act: -0.1700

Data Index: 6573859 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.6207. Min Act: -0.1700

Data Index: 5069115 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.6001. Min Act: -0.1700

Data Index: 6407758 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.6144. Min Act: -0.1700

Data Index: 5713238 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5922. Min Act: -0.1700

Data Index: 1901324 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5870. Min Act: -0.1700

Data Index: 8178664 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5813. Min Act: -0.1700

Data Index: 4615481 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5802. Min Act: -0.1700

Data Index: 5484442 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5804. Min Act: -0.1700

Data Index: 3510581 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5445. Min Act: -0.1700

Data Index: 6884559 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5393. Min Act: -0.1700

Data Index: 1525895 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5368. Min Act: -0.1700

Data Index: 2532144 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5352. Min Act: -0.1700

Data Index: 6734333 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5558. Min Act: -0.1700

Data Index: 4438004 (Open Web Text)

Max Activating Token Index: 18

Text #17

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5456. Min Act: -0.1700

Data Index: 4531329 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5458. Min Act: -0.1700

Data Index: 6634266 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.6672. Min Range: -3.6672

Max Act: 3.5346. Min Act: -0.1700

Data Index: 3043154 (Open Web Text)

Max Activating Token Index: 13