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

Dataset: Open Web Text

Neuron 2970 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: 4.0718. Min Range: -4.0718

Max Act: 4.0718. Min Act: -0.1700

Data Index: 2330192 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0718. Min Act: -0.1700

Data Index: 5550870 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0145. Min Act: -0.1700

Data Index: 1790433 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0009. Min Act: -0.1700

Data Index: 220483 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0067. Min Act: -0.1700

Data Index: 8561781 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0092. Min Act: -0.1700

Data Index: 8476626 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0025. Min Act: -0.1700

Data Index: 8365271 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0048. Min Act: -0.1700

Data Index: 8116352 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0284. Min Act: -0.1700

Data Index: 6092504 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.0718. Min Range: -4.0718

Max Act: 3.9986. Min Act: -0.1700

Data Index: 6021517 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0046. Min Act: -0.1700

Data Index: 5727225 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0026. Min Act: -0.1700

Data Index: 5575338 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0005. Min Act: -0.1700

Data Index: 5551730 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0228. Min Act: -0.1700

Data Index: 2909627 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0077. Min Act: -0.1700

Data Index: 2318289 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.0718. Min Range: -4.0718

Max Act: 4.0166. Min Act: -0.1700

Data Index: 5171610 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.0718. Min Range: -4.0718

Max Act: 3.9945. Min Act: -0.1700

Data Index: 4979072 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.0718. Min Range: -4.0718

Max Act: 3.9806. Min Act: -0.1700

Data Index: 5010435 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.0718. Min Range: -4.0718

Max Act: 3.9658. Min Act: -0.1700

Data Index: 5124410 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.0718. Min Range: -4.0718

Max Act: 3.9667. Min Act: -0.1700

Data Index: 1707212 (Open Web Text)

Max Activating Token Index: 6