Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3787 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4551. Min Range: -8.4551
Max Act: 8.4551. Min Act: -0.1700
Data Index: 5261040 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4551. Min Range: -8.4551
Max Act: 8.3926. Min Act: -0.1700
Data Index: 4775039 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.3926. Min Act: -0.1700
Data Index: 2366432 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4551. Min Range: -8.4551
Max Act: 7.2676. Min Act: -0.1700
Data Index: 8162037 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.9864. Min Act: -0.1700
Data Index: 5844106 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.9239. Min Act: -0.1700
Data Index: 3386073 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7989. Min Act: -0.1700
Data Index: 7606471 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7989. Min Act: -0.1700
Data Index: 5722551 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7676. Min Act: -0.1700
Data Index: 8261862 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7364. Min Act: -0.1700
Data Index: 604 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7364. Min Act: -0.1700
Data Index: 5844105 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7051. Min Act: -0.1700
Data Index: 5792925 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7051. Min Act: -0.1700
Data Index: 6724782 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.7051. Min Act: -0.1700
Data Index: 2354042 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.6739. Min Act: -0.1700
Data Index: 780376 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.6114. Min Act: -0.1700
Data Index: 2944872 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.5801. Min Act: -0.1700
Data Index: 4703052 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.5801. Min Act: -0.1700
Data Index: 3160946 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.5801. Min Act: -0.1700
Data Index: 5651505 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4551. Min Range: -8.4551
Max Act: 6.5489. Min Act: -0.1700
Data Index: 1205118 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19