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

Dataset: Open Web Text

Neuron 1327 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: 3.5904. Min Range: -3.5904

Max Act: 3.5904. Min Act: -0.1700

Data Index: 6557623 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5352. Min Act: -0.1700

Data Index: 3439 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5346. Min Act: -0.1700

Data Index: 3350350 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1148149 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5167. Min Act: -0.1700

Data Index: 159333 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4816. Min Act: -0.1700

Data Index: 4794747 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4972. Min Act: -0.1700

Data Index: 3892252 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4802. Min Act: -0.1700

Data Index: 3822637 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4922. Min Act: -0.1700

Data Index: 7756779 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5035. Min Act: -0.1700

Data Index: 6654945 (Open Web Text)

Max Activating Token Index: 12

Text #10

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5112. Min Act: -0.1700

Data Index: 1739149 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5068. Min Act: -0.1700

Data Index: 6215440 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4912. Min Act: -0.1700

Data Index: 5949323 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.5001. Min Act: -0.1700

Data Index: 3343476 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4857. Min Act: -0.1700

Data Index: 4275953 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4559. Min Act: -0.1700

Data Index: 1850662 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4559. Min Act: -0.1700

Data Index: 3862769 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4519. Min Act: -0.1700

Data Index: 87651 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4616. Min Act: -0.1700

Data Index: 3259569 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.5904. Min Range: -3.5904

Max Act: 3.4559. Min Act: -0.1700

Data Index: 781196 (Open Web Text)

Max Activating Token Index: 3