Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4992 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.7624. Min Act: -0.1700
Data Index: 7708981 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.4499. Min Act: -0.1700
Data Index: 3213378 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.4187. Min Act: -0.1700
Data Index: 7167227 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.3562. Min Act: -0.1700
Data Index: 244930 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.2624. Min Act: -0.1700
Data Index: 5353863 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.2624. Min Act: -0.1700
Data Index: 1211692 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1999. Min Act: -0.1700
Data Index: 6350455 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1999. Min Act: -0.1700
Data Index: 6145684 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1374. Min Act: -0.1700
Data Index: 1060137 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1062. Min Act: -0.1700
Data Index: 7206361 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1374. Min Act: -0.1700
Data Index: 8461994 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1374. Min Act: -0.1700
Data Index: 7100823 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1374. Min Act: -0.1700
Data Index: 8520179 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1062. Min Act: -0.1700
Data Index: 182233 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1062. Min Act: -0.1700
Data Index: 811894 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1062. Min Act: -0.1700
Data Index: 6767458 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.1062. Min Act: -0.1700
Data Index: 4606788 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.0749. Min Act: -0.1700
Data Index: 888644 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.0124. Min Act: -0.1700
Data Index: 165189 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7624. Min Range: -6.7624
Max Act: 6.0437. Min Act: -0.1700
Data Index: 81722 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19