Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 423 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.9833. Min Act: -0.1700
Data Index: 6656731 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.8895. Min Act: -0.1700
Data Index: 4341013 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.8270. Min Act: -0.1700
Data Index: 7773804 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.8270. Min Act: -0.1700
Data Index: 7358956 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.7958. Min Act: -0.1700
Data Index: 6986517 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.7645. Min Act: -0.1700
Data Index: 835088 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6708. Min Act: -0.1700
Data Index: 7998440 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.7020. Min Act: -0.1700
Data Index: 6716360 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6708. Min Act: -0.1700
Data Index: 8425356 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6708. Min Act: -0.1700
Data Index: 8010288 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6708. Min Act: -0.1700
Data Index: 6167523 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6708. Min Act: -0.1700
Data Index: 1473971 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7773805 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6395. Min Act: -0.1700
Data Index: 3411903 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6083. Min Act: -0.1700
Data Index: 1473978 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.6083. Min Act: -0.1700
Data Index: 8406873 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.5770. Min Act: -0.1700
Data Index: 1561217 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.5770. Min Act: -0.1700
Data Index: 1945121 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.5145. Min Act: -0.1700
Data Index: 7982863 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9833. Min Range: -5.9833
Max Act: 5.5145. Min Act: -0.1700
Data Index: 7441570 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19