Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1966 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3848. Min Range: -6.3848
Max Act: 6.3848. Min Act: -0.1700
Data Index: 6082821 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3848. Min Range: -6.3848
Max Act: 6.0723. Min Act: -0.1700
Data Index: 4862103 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3848. Min Range: -6.3848
Max Act: 6.0098. Min Act: -0.1700
Data Index: 6855301 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3848. Min Range: -6.3848
Max Act: 6.0410. Min Act: -0.1700
Data Index: 8065390 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3848. Min Range: -6.3848
Max Act: 6.0098. Min Act: -0.1700
Data Index: 2985896 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3848. Min Range: -6.3848
Max Act: 6.0098. Min Act: -0.1700
Data Index: 4415297 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.9473. Min Act: -0.1700
Data Index: 4377629 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.9160. Min Act: -0.1700
Data Index: 1218408 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.9473. Min Act: -0.1700
Data Index: 8484878 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.9785. Min Act: -0.1700
Data Index: 1390586 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.9785. Min Act: -0.1700
Data Index: 6818208 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.9160. Min Act: -0.1700
Data Index: 8670290 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.9160. Min Act: -0.1700
Data Index: 8484865 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.8223. Min Act: -0.1700
Data Index: 5571622 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.8223. Min Act: -0.1700
Data Index: 2067092 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.8535. Min Act: -0.1700
Data Index: 7071430 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.7910. Min Act: -0.1700
Data Index: 7858673 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.7910. Min Act: -0.1700
Data Index: 5780053 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.7910. Min Act: -0.1700
Data Index: 2839238 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3848. Min Range: -6.3848
Max Act: 5.7910. Min Act: -0.1700
Data Index: 3706838 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19