Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.7233. Min Act: -0.1700
Data Index: 1635439 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.7233. Min Act: -0.1700
Data Index: 4690002 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.7233. Min Act: -0.1700
Data Index: 1856191 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6920. Min Act: -0.1700
Data Index: 7930395 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6607. Min Act: -0.1700
Data Index: 8729597 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6137. Min Act: -0.1700
Data Index: 6133052 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6294. Min Act: -0.1700
Data Index: 8238764 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6137. Min Act: -0.1700
Data Index: 7599947 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6294. Min Act: -0.1700
Data Index: 746810 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6137. Min Act: -0.1700
Data Index: 3989788 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.6137. Min Act: -0.1700
Data Index: 7833327 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 8138941 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 5374899 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 3460120 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5824. Min Act: -0.1700
Data Index: 7199424 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 545437 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 8788318 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5668. Min Act: -0.1700
Data Index: 3343330 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5824. Min Act: -0.1700
Data Index: 8532946 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7233. Min Range: -3.7233
Max Act: 3.5824. Min Act: -0.1700
Data Index: 8374254 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19