Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2698 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2067. Min Range: -3.2067
Max Act: 3.2067. Min Act: -0.1700
Data Index: 7961100 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8910. Min Act: -0.1700
Data Index: 4369735 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8910. Min Act: -0.1700
Data Index: 719782 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8751. Min Act: -0.1700
Data Index: 2129995 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8593. Min Act: -0.1700
Data Index: 7736043 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8593. Min Act: -0.1700
Data Index: 5875881 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8434. Min Act: -0.1700
Data Index: 5893769 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8434. Min Act: -0.1700
Data Index: 8757052 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8275. Min Act: -0.1700
Data Index: 8453860 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8275. Min Act: -0.1700
Data Index: 8451012 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.8116. Min Act: -0.1700
Data Index: 4326655 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7797. Min Act: -0.1700
Data Index: 1219761 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7797. Min Act: -0.1700
Data Index: 2979389 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7956. Min Act: -0.1700
Data Index: 3147114 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7797. Min Act: -0.1700
Data Index: 5910643 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7956. Min Act: -0.1700
Data Index: 6885784 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7797. Min Act: -0.1700
Data Index: 8198194 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7638. Min Act: -0.1700
Data Index: 3142701 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7638. Min Act: -0.1700
Data Index: 6994405 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2067. Min Range: -3.2067
Max Act: 2.7478. Min Act: -0.1700
Data Index: 8254665 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19