Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2338. Min Range: -7.2338
Max Act: 7.2338. Min Act: -0.1700
Data Index: 5061996 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2338. Min Range: -7.2338
Max Act: 7.2025. Min Act: -0.1700
Data Index: 5061997 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2338. Min Range: -7.2338
Max Act: 7.1088. Min Act: -0.0819
Data Index: 348768 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2338. Min Range: -7.2338
Max Act: 7.0775. Min Act: -0.1700
Data Index: 1839353 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.9838. Min Act: -0.1700
Data Index: 2286200 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.9525. Min Act: -0.1699
Data Index: 6812869 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.9213. Min Act: -0.1689
Data Index: 1248247 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.9213. Min Act: -0.1681
Data Index: 4815421 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.8900. Min Act: -0.1700
Data Index: 7368965 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.8900. Min Act: -0.1700
Data Index: 3441183 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.8900. Min Act: -0.1700
Data Index: 1241218 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.8588. Min Act: -0.1700
Data Index: 4080624 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.8588. Min Act: -0.1700
Data Index: 7540229 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.7963. Min Act: -0.1700
Data Index: 6060689 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.7963. Min Act: -0.1698
Data Index: 6719682 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.7650. Min Act: -0.1698
Data Index: 578913 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.7338. Min Act: -0.1700
Data Index: 8124960 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.7338. Min Act: -0.1700
Data Index: 4274612 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.7025. Min Act: -0.1700
Data Index: 8251007 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2338. Min Range: -7.2338
Max Act: 6.7025. Min Act: -0.1700
Data Index: 6858844 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19