Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1273 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.3540. Min Act: -0.1700
Data Index: 8528115 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.2915. Min Act: -0.1700
Data Index: 5368832 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.2290. Min Act: -0.1700
Data Index: 7507633 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.1665. Min Act: -0.1700
Data Index: 3196839 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.1040. Min Act: -0.1700
Data Index: 6527727 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.0415. Min Act: -0.1700
Data Index: 154321 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.0415. Min Act: -0.1700
Data Index: 5794301 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.0415. Min Act: -0.1700
Data Index: 7342153 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3540. Min Range: -9.3540
Max Act: 9.0415. Min Act: -0.1700
Data Index: 3812510 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.9790. Min Act: -0.1700
Data Index: 5708500 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.9790. Min Act: -0.1700
Data Index: 7991613 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.9165. Min Act: -0.1700
Data Index: 5996426 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.9165. Min Act: -0.1700
Data Index: 3761866 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.9165. Min Act: -0.1700
Data Index: 5623058 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.8540. Min Act: -0.1700
Data Index: 7047395 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.7915. Min Act: -0.1700
Data Index: 817355 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.7290. Min Act: -0.1700
Data Index: 4976812 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.7290. Min Act: -0.1700
Data Index: 3186930 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.7915. Min Act: -0.1700
Data Index: 4066194 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3540. Min Range: -9.3540
Max Act: 8.7290. Min Act: -0.1700
Data Index: 3409669 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19