Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1110. Min Range: -13.1110
Max Act: 13.1110. Min Act: -0.1700
Data Index: 3545288 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1110. Min Range: -13.1110
Max Act: 13.0485. Min Act: -0.1700
Data Index: 2598183 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.9860. Min Act: -0.1700
Data Index: 4635674 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.7985. Min Act: -0.1700
Data Index: 6582785 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.7985. Min Act: -0.1700
Data Index: 6582781 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.7985. Min Act: -0.1700
Data Index: 8548718 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.7985. Min Act: -0.1700
Data Index: 5846395 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.7985. Min Act: -0.1700
Data Index: 2642989 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.7360. Min Act: -0.1700
Data Index: 5076991 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.7360. Min Act: -0.1700
Data Index: 6582783 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.6735. Min Act: -0.1700
Data Index: 6582786 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.6735. Min Act: -0.1700
Data Index: 2550543 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.6110. Min Act: -0.1700
Data Index: 2550544 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.5485. Min Act: -0.1700
Data Index: 3205199 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.4860. Min Act: -0.1700
Data Index: 8055073 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.5485. Min Act: -0.1700
Data Index: 7558966 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.5485. Min Act: -0.1700
Data Index: 6758148 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.5485. Min Act: -0.1700
Data Index: 2832630 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.6110. Min Act: -0.1700
Data Index: 2550551 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1110. Min Range: -13.1110
Max Act: 12.5485. Min Act: -0.1700
Data Index: 5547532 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19