Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4687. Min Range: -7.4687
Max Act: 7.4687. Min Act: -0.1700
Data Index: 7314492 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.9687. Min Act: -0.1700
Data Index: 6321865 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.9062. Min Act: -0.1700
Data Index: 4182657 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.8750. Min Act: -0.1700
Data Index: 1226301 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.8750. Min Act: -0.1700
Data Index: 4915178 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.7500. Min Act: -0.1700
Data Index: 4634710 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.7500. Min Act: -0.1700
Data Index: 6097239 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.6875. Min Act: -0.1700
Data Index: 5905474 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.7187. Min Act: -0.1700
Data Index: 1225021 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.6875. Min Act: -0.1700
Data Index: 4626836 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.6562. Min Act: -0.1700
Data Index: 5194984 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.6562. Min Act: -0.1700
Data Index: 1517338 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.6562. Min Act: -0.1700
Data Index: 8796788 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.6250. Min Act: -0.1700
Data Index: 4096306 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.5625. Min Act: -0.1700
Data Index: 5019251 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.5625. Min Act: -0.1700
Data Index: 8150273 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.5625. Min Act: -0.1700
Data Index: 4653748 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.5625. Min Act: -0.1700
Data Index: 4848285 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.5625. Min Act: -0.1700
Data Index: 2840161 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4687. Min Range: -7.4687
Max Act: 6.5312. Min Act: -0.1700
Data Index: 3387510 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19