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

Dataset: Open Web Text

Neuron 2663 in Layer 3

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: 3.8890. Min Range: -3.8890

Max Act: 3.8890. Min Act: -0.1700

Data Index: 797064 (Open Web Text)

Max Activating Token Index: 361

Text #1

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.7831. Min Act: -0.1700

Data Index: 2371289 (Open Web Text)

Max Activating Token Index: 225

Text #2

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.7699. Min Act: -0.1700

Data Index: 6256993 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.7361. Min Act: -0.1700

Data Index: 7124365 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.7307. Min Act: -0.1700

Data Index: 7972352 (Open Web Text)

Max Activating Token Index: 922

Text #5

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.7199. Min Act: -0.1700

Data Index: 287403 (Open Web Text)

Max Activating Token Index: 803

Text #6

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6704. Min Act: -0.1700

Data Index: 7472354 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6663. Min Act: -0.1700

Data Index: 1007727 (Open Web Text)

Max Activating Token Index: 620

Text #8

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6733. Min Act: -0.1700

Data Index: 5477955 (Open Web Text)

Max Activating Token Index: 784

Text #9

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6744. Min Act: -0.1700

Data Index: 317641 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6681. Min Act: -0.1700

Data Index: 925127 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6584. Min Act: -0.1700

Data Index: 3870544 (Open Web Text)

Max Activating Token Index: 620

Text #12

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6641. Min Act: -0.1700

Data Index: 2743622 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6595. Min Act: -0.1700

Data Index: 5926622 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6321. Min Act: -0.1700

Data Index: 5039427 (Open Web Text)

Max Activating Token Index: 799

Text #15

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6522. Min Act: -0.1700

Data Index: 5960538 (Open Web Text)

Max Activating Token Index: 287

Text #16

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6423. Min Act: -0.1700

Data Index: 6947735 (Open Web Text)

Max Activating Token Index: 522

Text #17

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6394. Min Act: -0.1700

Data Index: 7318794 (Open Web Text)

Max Activating Token Index: 77

Text #18

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6310. Min Act: -0.1700

Data Index: 1779380 (Open Web Text)

Max Activating Token Index: 679

Text #19

Max Range: 3.8890. Min Range: -3.8890

Max Act: 3.6459. Min Act: -0.1700

Data Index: 7371093 (Open Web Text)

Max Activating Token Index: 88