Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 2853 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')

Text #0

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.1016. Min Act: -0.1700

Data Index: 1268179 (Open Web Text)

Max Activating Token Index: 314

Text #1

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0385. Min Act: -0.1700

Data Index: 7436448 (Open Web Text)

Max Activating Token Index: 174

Text #2

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0227. Min Act: -0.1700

Data Index: 2491493 (Open Web Text)

Max Activating Token Index: 121

Text #3

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9911. Min Act: -0.1700

Data Index: 6504114 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9911. Min Act: -0.1700

Data Index: 5571912 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9911. Min Act: -0.1700

Data Index: 1152633 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9911. Min Act: -0.1700

Data Index: 4359533 (Open Web Text)

Max Activating Token Index: 75

Text #7

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9595. Min Act: -0.1700

Data Index: 679324 (Open Web Text)

Max Activating Token Index: 505

Text #8

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9753. Min Act: -0.1700

Data Index: 7195594 (Open Web Text)

Max Activating Token Index: 377

Text #9

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9911. Min Act: -0.1700

Data Index: 6156898 (Open Web Text)

Max Activating Token Index: 863

Text #10

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9595. Min Act: -0.1700

Data Index: 7272006 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9595. Min Act: -0.1700

Data Index: 493735 (Open Web Text)

Max Activating Token Index: 359

Text #12

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9595. Min Act: -0.1700

Data Index: 4185764 (Open Web Text)

Max Activating Token Index: 86

Text #13

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9753. Min Act: -0.1700

Data Index: 3176675 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9753. Min Act: -0.1700

Data Index: 2558943 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9278. Min Act: -0.1700

Data Index: 6593754 (Open Web Text)

Max Activating Token Index: 727

Text #16

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9437. Min Act: -0.1700

Data Index: 1947294 (Open Web Text)

Max Activating Token Index: 609

Text #17

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9278. Min Act: -0.1700

Data Index: 5037607 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.1016. Min Range: -3.1016

Max Act: 2.9595. Min Act: -0.1700

Data Index: 3769666 (Open Web Text)

Max Activating Token Index: 826

Text #19

Max Range: 3.1016. Min Range: -3.1016

Max Act: 3.0069. Min Act: -0.1700

Data Index: 6454962 (Open Web Text)

Max Activating Token Index: 503