Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.1368. Min Act: -0.1700
Data Index: 1148227 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.1053. Min Act: -0.1700
Data Index: 7454145 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0895. Min Act: -0.1700
Data Index: 7840483 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0737. Min Act: -0.1700
Data Index: 7464256 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0737. Min Act: -0.1700
Data Index: 6056407 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0579. Min Act: -0.1700
Data Index: 7412133 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0422. Min Act: -0.1700
Data Index: 7744632 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0579. Min Act: -0.1700
Data Index: 6699588 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0422. Min Act: -0.1700
Data Index: 4796089 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0422. Min Act: -0.1700
Data Index: 6077891 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5972343 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0422. Min Act: -0.1700
Data Index: 8349098 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0264. Min Act: -0.1700
Data Index: 1087236 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0264. Min Act: -0.1700
Data Index: 1473555 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0422. Min Act: -0.1700
Data Index: 934105 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0264. Min Act: -0.1700
Data Index: 2778449 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0106. Min Act: -0.1700
Data Index: 5714552 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1368. Min Range: -3.1368
Max Act: 3.0106. Min Act: -0.1700
Data Index: 7623304 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1368. Min Range: -3.1368
Max Act: 2.9948. Min Act: -0.1700
Data Index: 318976 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1368. Min Range: -3.1368
Max Act: 2.9948. Min Act: -0.1700
Data Index: 3944620 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19