Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.3460. Min Act: -0.1700
Data Index: 1524861 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.3460. Min Act: -0.1700
Data Index: 3429272 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.3148. Min Act: -0.1700
Data Index: 5412159 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.2835. Min Act: -0.1700
Data Index: 1090274 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.2835. Min Act: -0.1700
Data Index: 5220334 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.2523. Min Act: -0.1700
Data Index: 7495869 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.1898. Min Act: -0.1700
Data Index: 402302 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.1585. Min Act: -0.1700
Data Index: 1708712 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0960. Min Act: -0.1700
Data Index: 6091055 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0648. Min Act: -0.1700
Data Index: 5577690 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0648. Min Act: -0.1700
Data Index: 7114900 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0648. Min Act: -0.1700
Data Index: 4194490 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0648. Min Act: -0.1700
Data Index: 145117 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0335. Min Act: -0.1700
Data Index: 1900739 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0335. Min Act: -0.1700
Data Index: 3393992 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0335. Min Act: -0.1700
Data Index: 6091058 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0335. Min Act: -0.1700
Data Index: 6004073 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0023. Min Act: -0.1700
Data Index: 401025 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0023. Min Act: -0.1700
Data Index: 1983379 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3460. Min Range: -6.3460
Max Act: 6.0023. Min Act: -0.1700
Data Index: 2500981 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #19