Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 556 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0948. Min Range: -4.0948
Max Act: 4.0948. Min Act: -0.1700
Data Index: 51472 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0948. Min Range: -4.0948
Max Act: 4.0010. Min Act: -0.1700
Data Index: 8029526 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9385. Min Act: -0.1700
Data Index: 7519752 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8760. Min Act: -0.1700
Data Index: 4746624 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.9072. Min Act: -0.1700
Data Index: 8269805 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.8134. Min Act: -0.1700
Data Index: 4335371 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7665. Min Act: -0.1700
Data Index: 1039109 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7509. Min Act: -0.1700
Data Index: 1697286 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7665. Min Act: -0.1700
Data Index: 6415632 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7665. Min Act: -0.1700
Data Index: 285318 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7352. Min Act: -0.1700
Data Index: 7975366 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7509. Min Act: -0.1700
Data Index: 2189209 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7352. Min Act: -0.1700
Data Index: 7577691 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7509. Min Act: -0.1700
Data Index: 6124649 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7509. Min Act: -0.1700
Data Index: 7121195 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7821. Min Act: -0.1700
Data Index: 3340221 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7039. Min Act: -0.1700
Data Index: 5978056 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7196. Min Act: -0.1700
Data Index: 8340831 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7039. Min Act: -0.1700
Data Index: 5774440 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0948. Min Range: -4.0948
Max Act: 3.7196. Min Act: -0.1700
Data Index: 4556266 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #19