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

Dataset: Open Web Text

Neuron 98 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: 2.9552. Min Range: -2.9552

Max Act: 2.9463. Min Act: -0.1700

Data Index: 4717172 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9469. Min Act: -0.1700

Data Index: 5773439 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9522. Min Act: -0.1700

Data Index: 5615629 (Open Web Text)

Max Activating Token Index: 217

Text #3

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9552. Min Act: -0.1700

Data Index: 3872909 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9504. Min Act: -0.1700

Data Index: 4886949 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9379. Min Act: -0.1700

Data Index: 1066188 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9026. Min Act: -0.1700

Data Index: 7367765 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9091. Min Act: -0.1700

Data Index: 5003265 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9117. Min Act: -0.1700

Data Index: 1077490 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.8942. Min Act: -0.1700

Data Index: 6708524 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.8942. Min Act: -0.1700

Data Index: 2598679 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9021. Min Act: -0.1700

Data Index: 4133869 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9046. Min Act: -0.1700

Data Index: 347064 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9021. Min Act: -0.1700

Data Index: 4116734 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.9039. Min Act: -0.1700

Data Index: 323966 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.8972. Min Act: -0.1700

Data Index: 5435606 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.8942. Min Act: -0.1700

Data Index: 4223689 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.8849. Min Act: -0.1700

Data Index: 5714215 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.8829. Min Act: -0.1700

Data Index: 4659096 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.9552. Min Range: -2.9552

Max Act: 2.8849. Min Act: -0.1700

Data Index: 6391409 (Open Web Text)

Max Activating Token Index: 2