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

Dataset: Open Web Text

Neuron 1869 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: 3.1611. Min Range: -3.1611

Max Act: 3.1531. Min Act: -0.1700

Data Index: 3585786 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1611. Min Act: -0.1700

Data Index: 4644911 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1558. Min Act: -0.1700

Data Index: 6229520 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1460. Min Act: -0.1700

Data Index: 8124977 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1454. Min Act: -0.1700

Data Index: 5419700 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1438. Min Act: -0.1700

Data Index: 3474793 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1197. Min Act: -0.1700

Data Index: 4316859 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1253. Min Act: -0.1700

Data Index: 8587675 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1227. Min Act: -0.1700

Data Index: 7484285 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1129. Min Act: -0.1700

Data Index: 4430174 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1129. Min Act: -0.1700

Data Index: 5303818 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.1121. Min Act: -0.1700

Data Index: 5512459 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0923. Min Act: -0.1700

Data Index: 138799 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0732. Min Act: -0.1700

Data Index: 5512460 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0536. Min Act: -0.1700

Data Index: 3652399 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0604. Min Act: -0.1700

Data Index: 8088107 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0634. Min Act: -0.1700

Data Index: 5105128 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0569. Min Act: -0.1700

Data Index: 6199900 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0494. Min Act: -0.1700

Data Index: 1569891 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.1611. Min Range: -3.1611

Max Act: 3.0521. Min Act: -0.1700

Data Index: 4662439 (Open Web Text)

Max Activating Token Index: 4