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

Dataset: Open Web Text

Neuron 2620 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: 3.9792. Min Range: -3.9792

Max Act: 3.9792. Min Act: -0.1700

Data Index: 3700627 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9573. Min Act: -0.1700

Data Index: 6392485 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9469. Min Act: -0.1700

Data Index: 5125503 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9596. Min Act: -0.1700

Data Index: 1059813 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9333. Min Act: -0.1700

Data Index: 2075537 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9122. Min Act: -0.1700

Data Index: 8484068 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9102. Min Act: -0.1700

Data Index: 2016882 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9177. Min Act: -0.1700

Data Index: 6801855 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8954. Min Act: -0.1700

Data Index: 7666116 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8943. Min Act: -0.1700

Data Index: 7628529 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8960. Min Act: -0.1700

Data Index: 7172216 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9023. Min Act: -0.1700

Data Index: 2521557 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8986. Min Act: -0.1700

Data Index: 1965650 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.9019. Min Act: -0.1700

Data Index: 5856988 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8941. Min Act: -0.1700

Data Index: 3718090 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8915. Min Act: -0.1700

Data Index: 5900531 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8920. Min Act: -0.1700

Data Index: 4783535 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8807. Min Act: -0.1700

Data Index: 5004731 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8830. Min Act: -0.1700

Data Index: 565890 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.9792. Min Range: -3.9792

Max Act: 3.8846. Min Act: -0.1700

Data Index: 6198170 (Open Web Text)

Max Activating Token Index: 4