Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.8654. Min Act: -0.1700
Data Index: 7056103 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.8029. Min Act: -0.1700
Data Index: 3437854 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.6154. Min Act: -0.1700
Data Index: 1226401 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.3654. Min Act: -0.1700
Data Index: 6258727 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.2092. Min Act: -0.1700
Data Index: 1891265 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.2404. Min Act: -0.1700
Data Index: 6942523 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.2092. Min Act: -0.1700
Data Index: 2622970 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.1779. Min Act: -0.1700
Data Index: 8362531 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.2092. Min Act: -0.1700
Data Index: 8069148 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.1779. Min Act: -0.1700
Data Index: 6258728 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.1779. Min Act: -0.1700
Data Index: 1644273 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.1467. Min Act: -0.1700
Data Index: 4058714 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.1467. Min Act: -0.1700
Data Index: 8333393 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.1467. Min Act: -0.1700
Data Index: 6579674 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.1154. Min Act: -0.1700
Data Index: 6467774 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.0842. Min Act: -0.1700
Data Index: 3413021 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.0842. Min Act: -0.1700
Data Index: 1781084 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.0842. Min Act: -0.1700
Data Index: 5833581 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.0842. Min Act: -0.1700
Data Index: 4052485 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8654. Min Range: -8.8654
Max Act: 8.0842. Min Act: -0.1700
Data Index: 5143 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19