Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3493 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.3850. Min Act: -0.1700
Data Index: 4635854 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.3850. Min Act: -0.1700
Data Index: 6840950 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.3225. Min Act: -0.1700
Data Index: 3932887 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.2600. Min Act: -0.1700
Data Index: 1568047 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.2600. Min Act: -0.1700
Data Index: 1403747 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.1975. Min Act: -0.1700
Data Index: 3385686 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.2600. Min Act: -0.1700
Data Index: 7093705 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.1975. Min Act: -0.1700
Data Index: 3689133 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.1975. Min Act: -0.1700
Data Index: 5031253 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.1350. Min Act: -0.1700
Data Index: 7762360 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.1350. Min Act: -0.1700
Data Index: 6147000 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.1350. Min Act: -0.1700
Data Index: 8831268 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 1803158 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.1350. Min Act: -0.1700
Data Index: 8469781 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 7820058 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 2448022 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 3281084 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 1599443 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 4140602 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3850. Min Range: -8.3850
Max Act: 8.0725. Min Act: -0.1700
Data Index: 5678737 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19