Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.7428. Min Act: -0.1700
Data Index: 54675 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.5865. Min Act: -0.1700
Data Index: 3365960 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.5553. Min Act: -0.1700
Data Index: 7313186 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.5553. Min Act: -0.1700
Data Index: 470741 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.4615. Min Act: -0.1700
Data Index: 5567339 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.4303. Min Act: -0.1700
Data Index: 5838070 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.3678. Min Act: -0.1700
Data Index: 2832495 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.3365. Min Act: -0.1700
Data Index: 8164102 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.3678. Min Act: -0.1700
Data Index: 2144775 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.3365. Min Act: -0.1700
Data Index: 4902023 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.3053. Min Act: -0.1700
Data Index: 1402818 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.2428. Min Act: -0.1700
Data Index: 1792642 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.2428. Min Act: -0.1700
Data Index: 6570444 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.1490. Min Act: -0.1700
Data Index: 2932838 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.1490. Min Act: -0.1700
Data Index: 2237920 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.1178. Min Act: -0.1700
Data Index: 7156800 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.1178. Min Act: -0.1700
Data Index: 5957906 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.1178. Min Act: -0.1700
Data Index: 1108024 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.1178. Min Act: -0.1700
Data Index: 341047 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7428. Min Range: -6.7428
Max Act: 6.0865. Min Act: -0.1700
Data Index: 3960575 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19