Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.8198. Min Act: -0.1700
Data Index: 1957418 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.5385. Min Act: -0.1700
Data Index: 2284348 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.5073. Min Act: -0.1700
Data Index: 7581575 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4760. Min Act: -0.1700
Data Index: 7729445 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4135. Min Act: -0.1700
Data Index: 6637393 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4448. Min Act: -0.1700
Data Index: 461386 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4135. Min Act: -0.1700
Data Index: 2823079 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4135. Min Act: -0.1700
Data Index: 3478197 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4135. Min Act: -0.1700
Data Index: 4903038 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4135. Min Act: -0.1700
Data Index: 4121365 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.4135. Min Act: -0.1700
Data Index: 2823873 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3823. Min Act: -0.1700
Data Index: 7842613 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3823. Min Act: -0.1699
Data Index: 5102009 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3823. Min Act: -0.1700
Data Index: 4473210 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3510. Min Act: -0.1700
Data Index: 794354 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3510. Min Act: -0.1700
Data Index: 2823080 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3198. Min Act: -0.1700
Data Index: 588165 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3510. Min Act: -0.1700
Data Index: 5198177 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3198. Min Act: -0.1700
Data Index: 7094994 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8198. Min Range: -5.8198
Max Act: 5.3198. Min Act: -0.1700
Data Index: 597363 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19