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

Dataset: Open Web Text

Neuron 1877 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: 4.0944. Min Range: -4.0944

Max Act: 4.0944. Min Act: -0.1700

Data Index: 3698723 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9656. Min Act: -0.1700

Data Index: 6881520 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9658. Min Act: -0.1700

Data Index: 6460944 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9736. Min Act: -0.1700

Data Index: 8207262 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9464. Min Act: -0.1700

Data Index: 2831157 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9575. Min Act: -0.1700

Data Index: 8387822 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9454. Min Act: -0.1700

Data Index: 5045077 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9113. Min Act: -0.1700

Data Index: 6570629 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9194. Min Act: -0.1700

Data Index: 5141046 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9195. Min Act: -0.1700

Data Index: 57413 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.9287. Min Act: -0.1700

Data Index: 4931630 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8777. Min Act: -0.1700

Data Index: 5271924 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8839. Min Act: -0.1700

Data Index: 1362209 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8781. Min Act: -0.1700

Data Index: 6890188 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8806. Min Act: -0.1700

Data Index: 5455191 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8815. Min Act: -0.1700

Data Index: 866218 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8895. Min Act: -0.1700

Data Index: 8801456 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8946. Min Act: -0.1700

Data Index: 6031982 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8886. Min Act: -0.1700

Data Index: 6479956 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0944. Min Range: -4.0944

Max Act: 3.8758. Min Act: -0.1700

Data Index: 4467688 (Open Web Text)

Max Activating Token Index: 5