Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1537 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.2752. Min Act: -0.1700
Data Index: 1324998 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.1502. Min Act: -0.1700
Data Index: 4589413 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.2127. Min Act: -0.1700
Data Index: 7780608 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.1502. Min Act: -0.1700
Data Index: 980812 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.1189. Min Act: -0.1700
Data Index: 8802026 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.0877. Min Act: -0.1700
Data Index: 8560682 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.0877. Min Act: -0.1700
Data Index: 2481055 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.0564. Min Act: -0.1700
Data Index: 5622031 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.0564. Min Act: -0.1700
Data Index: 8443785 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.0564. Min Act: -0.1700
Data Index: 1296792 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.0564. Min Act: -0.1700
Data Index: 6386943 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.9939. Min Act: -0.1700
Data Index: 187725 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2752. Min Range: -7.2752
Max Act: 7.0252. Min Act: -0.1700
Data Index: 5374626 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.9939. Min Act: -0.1700
Data Index: 7422093 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.9939. Min Act: -0.1700
Data Index: 1671418 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.9939. Min Act: -0.1700
Data Index: 5021278 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.9627. Min Act: -0.1700
Data Index: 2221827 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.9939. Min Act: -0.1700
Data Index: 4676757 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.9314. Min Act: -0.1700
Data Index: 8327964 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2752. Min Range: -7.2752
Max Act: 6.8689. Min Act: -0.1700
Data Index: 660578 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19