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

Dataset: Open Web Text

Neuron 1464 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: 2.9685. Min Range: -2.9685

Max Act: 2.9685. Min Act: -0.1700

Data Index: 5512950 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9368. Min Act: -0.1700

Data Index: 7967078 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9525. Min Act: -0.1700

Data Index: 1539691 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9349. Min Act: -0.1700

Data Index: 6746982 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9313. Min Act: -0.1700

Data Index: 3196607 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9192. Min Act: -0.1700

Data Index: 5424166 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9288. Min Act: -0.1700

Data Index: 8597530 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9225. Min Act: -0.1700

Data Index: 6255577 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9119. Min Act: -0.1700

Data Index: 50475 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9083. Min Act: -0.1700

Data Index: 7882419 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9135. Min Act: -0.1700

Data Index: 1761521 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9089. Min Act: -0.1700

Data Index: 4785288 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.8919. Min Act: -0.1700

Data Index: 113195 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.8990. Min Act: -0.1700

Data Index: 5466409 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.8971. Min Act: -0.1700

Data Index: 6226713 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.8919. Min Act: -0.1700

Data Index: 311026 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.8888. Min Act: -0.1700

Data Index: 1774576 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.9000. Min Act: -0.1700

Data Index: 6417936 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.8966. Min Act: -0.1700

Data Index: 6436997 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 2.9685. Min Range: -2.9685

Max Act: 2.8880. Min Act: -0.1700

Data Index: 6634405 (Open Web Text)

Max Activating Token Index: 2