Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5677 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0087. Min Range: -8.0087
Max Act: 8.0087. Min Act: -0.1700
Data Index: 3303305 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.7275. Min Act: -0.1700
Data Index: 4499444 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.5712. Min Act: -0.1700
Data Index: 2419382 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.5712. Min Act: -0.1700
Data Index: 1120676 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.5400. Min Act: -0.1700
Data Index: 5928826 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.4775. Min Act: -0.1700
Data Index: 1617681 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.4775. Min Act: -0.1700
Data Index: 2992677 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.4462. Min Act: -0.1700
Data Index: 8610776 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.4462. Min Act: -0.1700
Data Index: 4596571 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.4462. Min Act: -0.1700
Data Index: 1808948 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.3837. Min Act: -0.1700
Data Index: 3506927 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.3525. Min Act: -0.1700
Data Index: 6021082 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.3837. Min Act: -0.1700
Data Index: 1107067 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.3525. Min Act: -0.1700
Data Index: 1785173 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.2900. Min Act: -0.1700
Data Index: 6941186 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.2900. Min Act: -0.1700
Data Index: 4732932 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.2587. Min Act: -0.1700
Data Index: 2077978 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.2587. Min Act: -0.1700
Data Index: 5516983 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.2587. Min Act: -0.1700
Data Index: 103881 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0087. Min Range: -8.0087
Max Act: 7.2275. Min Act: -0.1700
Data Index: 5969884 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19