Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 57 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1941. Min Range: -6.1941
Max Act: 6.1941. Min Act: -0.1700
Data Index: 5737464 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1941. Min Range: -6.1941
Max Act: 6.1941. Min Act: -0.1700
Data Index: 6912846 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1941. Min Range: -6.1941
Max Act: 6.1628. Min Act: -0.1700
Data Index: 2857845 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1941. Min Range: -6.1941
Max Act: 6.0378. Min Act: -0.1700
Data Index: 1908907 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1941. Min Range: -6.1941
Max Act: 6.0691. Min Act: -0.1700
Data Index: 4730422 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1941. Min Range: -6.1941
Max Act: 6.0066. Min Act: -0.1700
Data Index: 1992341 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1941. Min Range: -6.1941
Max Act: 6.0378. Min Act: -0.1700
Data Index: 7008562 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.9753. Min Act: -0.1700
Data Index: 3806719 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.8816. Min Act: -0.1700
Data Index: 2707991 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.8191. Min Act: -0.1700
Data Index: 3971389 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.7566. Min Act: -0.1700
Data Index: 1737551 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.7566. Min Act: -0.1700
Data Index: 1598442 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.7566. Min Act: -0.1700
Data Index: 1551734 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.7253. Min Act: -0.1700
Data Index: 8301379 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.6941. Min Act: -0.1700
Data Index: 2265876 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.6628. Min Act: -0.1700
Data Index: 6507092 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.6628. Min Act: -0.1700
Data Index: 2265416 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.6003. Min Act: -0.1700
Data Index: 5528235 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.6316. Min Act: -0.1700
Data Index: 4229350 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1941. Min Range: -6.1941
Max Act: 5.5691. Min Act: -0.1700
Data Index: 4336426 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19