Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5024 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1274. Min Range: -7.1274
Max Act: 7.1274. Min Act: -0.1700
Data Index: 3392217 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.8774. Min Act: -0.1700
Data Index: 6196765 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7524. Min Act: -0.1700
Data Index: 7637762 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6899. Min Act: -0.1700
Data Index: 6052145 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.7211. Min Act: -0.1700
Data Index: 1207258 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6899. Min Act: -0.1700
Data Index: 2215824 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6274. Min Act: -0.1700
Data Index: 3549401 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.6586. Min Act: -0.1700
Data Index: 8361915 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5649. Min Act: -0.1700
Data Index: 2085769 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5649. Min Act: -0.1700
Data Index: 8092496 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5649. Min Act: -0.1700
Data Index: 723413 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5649. Min Act: -0.1700
Data Index: 7997228 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5336. Min Act: -0.1700
Data Index: 5965404 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5336. Min Act: -0.1700
Data Index: 2261904 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5336. Min Act: -0.1700
Data Index: 7358319 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5336. Min Act: -0.1700
Data Index: 1203580 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5024. Min Act: -0.1700
Data Index: 4306234 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5024. Min Act: -0.1700
Data Index: 434155 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.5024. Min Act: -0.1700
Data Index: 946923 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1274. Min Range: -7.1274
Max Act: 6.4711. Min Act: -0.1700
Data Index: 1318015 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19