Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 124 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8072. Min Range: -6.8072
Max Act: 6.8072. Min Act: -0.1700
Data Index: 6510620 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8072. Min Range: -6.8072
Max Act: 6.4947. Min Act: -0.1700
Data Index: 6792197 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8072. Min Range: -6.8072
Max Act: 6.2759. Min Act: -0.1700
Data Index: 178298 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8072. Min Range: -6.8072
Max Act: 6.2759. Min Act: -0.1700
Data Index: 7904625 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8072. Min Range: -6.8072
Max Act: 6.0572. Min Act: -0.1700
Data Index: 2974937 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9947. Min Act: -0.1700
Data Index: 5383632 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9947. Min Act: -0.1700
Data Index: 7482373 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9634. Min Act: -0.1700
Data Index: 7261446 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9947. Min Act: -0.1700
Data Index: 8505054 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9322. Min Act: -0.1700
Data Index: 2187323 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9634. Min Act: -0.1700
Data Index: 2500139 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9009. Min Act: -0.1700
Data Index: 8441714 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9322. Min Act: -0.1700
Data Index: 8472859 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9322. Min Act: -0.1700
Data Index: 8654065 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.8697. Min Act: -0.1700
Data Index: 8564665 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9009. Min Act: -0.1700
Data Index: 8369493 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.8697. Min Act: -0.1700
Data Index: 6290425 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.8384. Min Act: -0.1700
Data Index: 560196 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.8697. Min Act: -0.1700
Data Index: 4488813 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8072. Min Range: -6.8072
Max Act: 5.9009. Min Act: -0.1700
Data Index: 562201 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19