Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5548 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.3267. Min Act: -0.1698
Data Index: 4550179 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.2329. Min Act: -0.1677
Data Index: 7498575 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.2017. Min Act: -0.1700
Data Index: 4842411 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.1079. Min Act: -0.1697
Data Index: 3497950 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.0767. Min Act: -0.1700
Data Index: 8592011 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.0767. Min Act: -0.1700
Data Index: 1653262 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.0767. Min Act: -0.1700
Data Index: 3712205 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3267. Min Range: -8.3267
Max Act: 8.0767. Min Act: -0.1698
Data Index: 8169998 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.9829. Min Act: -0.1700
Data Index: 4469279 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.9517. Min Act: -0.1697
Data Index: 4443439 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.9204. Min Act: -0.1700
Data Index: 6832212 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.8579. Min Act: -0.1700
Data Index: 5819834 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.9204. Min Act: -0.1693
Data Index: 1141027 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.8579. Min Act: -0.1700
Data Index: 6141998 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.8579. Min Act: -0.1691
Data Index: 3806645 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.9204. Min Act: -0.1700
Data Index: 8116708 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.8579. Min Act: -0.1698
Data Index: 7079639 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.8892. Min Act: -0.1700
Data Index: 6955065 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.8267. Min Act: -0.1700
Data Index: 2824961 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3267. Min Range: -8.3267
Max Act: 7.8892. Min Act: -0.1700
Data Index: 1936309 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19