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

Dataset: Open Web Text

Neuron 2746 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: 3.3987. Min Range: -3.3987

Max Act: 3.3987. Min Act: -0.1700

Data Index: 1127437 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3736. Min Act: -0.1700

Data Index: 1230262 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3552. Min Act: -0.1700

Data Index: 5430474 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3586. Min Act: -0.1700

Data Index: 5434550 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3275. Min Act: -0.1700

Data Index: 3568525 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3657. Min Act: -0.1700

Data Index: 4066018 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3165. Min Act: -0.1700

Data Index: 6270834 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3080. Min Act: -0.1700

Data Index: 7685526 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3350. Min Act: -0.1700

Data Index: 202479 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3343. Min Act: -0.1700

Data Index: 7773704 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3155. Min Act: -0.1700

Data Index: 5333262 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3088. Min Act: -0.1700

Data Index: 1030411 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3110. Min Act: -0.1700

Data Index: 3975892 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3240. Min Act: -0.1700

Data Index: 4046020 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2722. Min Act: -0.1700

Data Index: 251192 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2722. Min Act: -0.1700

Data Index: 4991190 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2722. Min Act: -0.1700

Data Index: 4657145 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2722. Min Act: -0.1700

Data Index: 3279501 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.2722. Min Act: -0.1700

Data Index: 632861 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.3987. Min Range: -3.3987

Max Act: 3.3035. Min Act: -0.1700

Data Index: 2582313 (Open Web Text)

Max Activating Token Index: 3