Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.4290. Min Act: -0.1700
Data Index: 8453778 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.3353. Min Act: -0.1700
Data Index: 6951301 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.3353. Min Act: -0.1700
Data Index: 2324596 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.2415. Min Act: -0.1700
Data Index: 5945936 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.1790. Min Act: -0.1700
Data Index: 3984258 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.1478. Min Act: -0.1700
Data Index: 5313122 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.1165. Min Act: -0.1700
Data Index: 868685 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.0853. Min Act: -0.1700
Data Index: 7981553 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.0228. Min Act: -0.1700
Data Index: 3538428 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.0540. Min Act: -0.1700
Data Index: 1285078 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.9603. Min Act: -0.1700
Data Index: 6211250 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4290. Min Range: -7.4290
Max Act: 7.0228. Min Act: -0.1700
Data Index: 2217213 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.9603. Min Act: -0.1700
Data Index: 3465125 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.9603. Min Act: -0.1700
Data Index: 8039075 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.9290. Min Act: -0.1700
Data Index: 4087675 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.9290. Min Act: -0.1700
Data Index: 2861788 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.9290. Min Act: -0.1700
Data Index: 5625845 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.8978. Min Act: -0.1700
Data Index: 2500708 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.9290. Min Act: -0.1700
Data Index: 6271291 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4290. Min Range: -7.4290
Max Act: 6.8978. Min Act: -0.1700
Data Index: 7846446 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19