Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 215 in Layer 20

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1016. Min Range: -7.1016

Max Act: 7.1016. Min Act: -0.1700

Data Index: 4722402 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 7.1016. Min Range: -7.1016

Max Act: 7.0079. Min Act: -0.1700

Data Index: 3538771 (Open Web Text)

Max Activating Token Index: 569

Text #2

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9766. Min Act: -0.1700

Data Index: 8564255 (Open Web Text)

Max Activating Token Index: 499

Text #3

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9454. Min Act: -0.1700

Data Index: 550732 (Open Web Text)

Max Activating Token Index: 806

Text #4

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9454. Min Act: -0.1700

Data Index: 3994520 (Open Web Text)

Max Activating Token Index: 937

Text #5

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9454. Min Act: -0.1700

Data Index: 3208442 (Open Web Text)

Max Activating Token Index: 424

Text #6

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9141. Min Act: -0.1700

Data Index: 6819501 (Open Web Text)

Max Activating Token Index: 278

Text #7

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9141. Min Act: -0.1700

Data Index: 7750297 (Open Web Text)

Max Activating Token Index: 637

Text #8

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.9141. Min Act: -0.1700

Data Index: 3392393 (Open Web Text)

Max Activating Token Index: 698

Text #9

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8829. Min Act: -0.1700

Data Index: 3462758 (Open Web Text)

Max Activating Token Index: 511

Text #10

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7891. Min Act: -0.1700

Data Index: 1365875 (Open Web Text)

Max Activating Token Index: 640

Text #11

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7891. Min Act: -0.1700

Data Index: 7637092 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8204. Min Act: -0.1700

Data Index: 4143642 (Open Web Text)

Max Activating Token Index: 127

Text #13

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8204. Min Act: -0.1700

Data Index: 5247715 (Open Web Text)

Max Activating Token Index: 281

Text #14

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7891. Min Act: -0.1700

Data Index: 6970268 (Open Web Text)

Max Activating Token Index: 400

Text #15

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.8204. Min Act: -0.1700

Data Index: 4127291 (Open Web Text)

Max Activating Token Index: 27

Text #16

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7891. Min Act: -0.1700

Data Index: 3824231 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7579. Min Act: -0.1700

Data Index: 4120222 (Open Web Text)

Max Activating Token Index: 1013

Text #18

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7579. Min Act: -0.1700

Data Index: 2993394 (Open Web Text)

Max Activating Token Index: 471

Text #19

Max Range: 7.1016. Min Range: -7.1016

Max Act: 6.7579. Min Act: -0.1700

Data Index: 6130260 (Open Web Text)

Max Activating Token Index: 746