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

Dataset: Open Web Text

Neuron 804 in Layer 4

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: 4.3824. Min Range: -4.3824

Max Act: 4.3824. Min Act: -0.1700

Data Index: 3676406 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.3754. Min Act: -0.1700

Data Index: 1066159 (Open Web Text)

Max Activating Token Index: 840

Text #2

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.3459. Min Act: -0.1700

Data Index: 8830077 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.2840. Min Act: -0.1700

Data Index: 5809042 (Open Web Text)

Max Activating Token Index: 610

Text #4

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.2774. Min Act: -0.1700

Data Index: 7584890 (Open Web Text)

Max Activating Token Index: 444

Text #5

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.2674. Min Act: -0.1700

Data Index: 1204148 (Open Web Text)

Max Activating Token Index: 252

Text #6

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.2327. Min Act: -0.1700

Data Index: 1664518 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1881. Min Act: -0.1700

Data Index: 233435 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.2028. Min Act: -0.1700

Data Index: 6756991 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1739. Min Act: -0.1700

Data Index: 1986940 (Open Web Text)

Max Activating Token Index: 975

Text #10

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1421. Min Act: -0.1700

Data Index: 1204130 (Open Web Text)

Max Activating Token Index: 990

Text #11

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1316. Min Act: -0.1700

Data Index: 3846422 (Open Web Text)

Max Activating Token Index: 550

Text #12

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1448. Min Act: -0.1700

Data Index: 5545428 (Open Web Text)

Max Activating Token Index: 718

Text #13

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1447. Min Act: -0.1700

Data Index: 1204132 (Open Web Text)

Max Activating Token Index: 607

Text #14

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1413. Min Act: -0.1700

Data Index: 6042329 (Open Web Text)

Max Activating Token Index: 680

Text #15

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1252. Min Act: -0.1700

Data Index: 8416057 (Open Web Text)

Max Activating Token Index: 573

Text #16

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1123. Min Act: -0.1700

Data Index: 7023474 (Open Web Text)

Max Activating Token Index: 592

Text #17

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1059. Min Act: -0.1700

Data Index: 1204134 (Open Web Text)

Max Activating Token Index: 912

Text #18

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.1068. Min Act: -0.1700

Data Index: 2282483 (Open Web Text)

Max Activating Token Index: 262

Text #19

Max Range: 4.3824. Min Range: -4.3824

Max Act: 4.0770. Min Act: -0.1700

Data Index: 162605 (Open Web Text)

Max Activating Token Index: 614