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

Dataset: Open Web Text

Neuron 239 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: 2.7655. Min Range: -2.7655

Max Act: 2.7655. Min Act: -0.1700

Data Index: 4216990 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6828. Min Act: -0.1700

Data Index: 3334542 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6636. Min Act: -0.1700

Data Index: 2116370 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6447. Min Act: -0.1700

Data Index: 238287 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6432. Min Act: -0.1700

Data Index: 8815011 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6271. Min Act: -0.1700

Data Index: 6102536 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6255. Min Act: -0.1700

Data Index: 8801837 (Open Web Text)

Max Activating Token Index: 264

Text #7

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6400. Min Act: -0.1700

Data Index: 6864450 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6398. Min Act: -0.1700

Data Index: 3850074 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6226. Min Act: -0.1700

Data Index: 6400877 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6163. Min Act: -0.1700

Data Index: 8361451 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6062. Min Act: -0.1700

Data Index: 8553869 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.6093. Min Act: -0.1700

Data Index: 5004653 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.5987. Min Act: -0.1700

Data Index: 5555742 (Open Web Text)

Max Activating Token Index: 47

Text #14

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.5869. Min Act: -0.1700

Data Index: 4496918 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.5864. Min Act: -0.1700

Data Index: 2113819 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.5880. Min Act: -0.1700

Data Index: 7071776 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.5746. Min Act: -0.1700

Data Index: 625820 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.5847. Min Act: -0.1700

Data Index: 7494106 (Open Web Text)

Max Activating Token Index: 378

Text #19

Max Range: 2.7655. Min Range: -2.7655

Max Act: 2.5877. Min Act: -0.1700

Data Index: 1234799 (Open Web Text)

Max Activating Token Index: 3