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

Dataset: Open Web Text

Neuron 932 in Layer 1

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: 1.9042. Min Range: -1.9042

Max Act: 1.9042. Min Act: -0.1700

Data Index: 8467037 (Open Web Text)

Max Activating Token Index: 425

Text #1

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8896. Min Act: -0.1700

Data Index: 2105271 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8717. Min Act: -0.1700

Data Index: 3290106 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8544. Min Act: -0.1700

Data Index: 4261575 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8501. Min Act: -0.1700

Data Index: 6811861 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8497. Min Act: -0.1699

Data Index: 3992065 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8446. Min Act: -0.1699

Data Index: 3992067 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8394. Min Act: -0.1700

Data Index: 7218263 (Open Web Text)

Max Activating Token Index: 885

Text #8

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8353. Min Act: -0.1700

Data Index: 8119517 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8358. Min Act: -0.1700

Data Index: 5614102 (Open Web Text)

Max Activating Token Index: 387

Text #10

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8347. Min Act: -0.1700

Data Index: 1806955 (Open Web Text)

Max Activating Token Index: 217

Text #11

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8274. Min Act: -0.1698

Data Index: 3442805 (Open Web Text)

Max Activating Token Index: 134

Text #12

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8194. Min Act: -0.1700

Data Index: 2476404 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8112. Min Act: -0.1700

Data Index: 5561827 (Open Web Text)

Max Activating Token Index: 412

Text #14

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8042. Min Act: -0.1700

Data Index: 3924356 (Open Web Text)

Max Activating Token Index: 394

Text #15

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8145. Min Act: -0.1700

Data Index: 442821 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8060. Min Act: -0.1700

Data Index: 1121324 (Open Web Text)

Max Activating Token Index: 470

Text #17

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.7995. Min Act: -0.1700

Data Index: 6863756 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8012. Min Act: -0.1700

Data Index: 3575233 (Open Web Text)

Max Activating Token Index: 736

Text #19

Max Range: 1.9042. Min Range: -1.9042

Max Act: 1.8018. Min Act: -0.1700

Data Index: 5581921 (Open Web Text)

Max Activating Token Index: 269