Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5726 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7088. Min Range: -6.7088
Max Act: 6.7088. Min Act: -0.1700
Data Index: 5870858 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7088. Min Range: -6.7088
Max Act: 6.4588. Min Act: -0.1700
Data Index: 7987478 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7088. Min Range: -6.7088
Max Act: 6.1150. Min Act: -0.1700
Data Index: 2187176 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7088. Min Range: -6.7088
Max Act: 6.0525. Min Act: -0.1700
Data Index: 3995534 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7088. Min Range: -6.7088
Max Act: 6.0525. Min Act: -0.1700
Data Index: 4581163 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7088. Min Range: -6.7088
Max Act: 6.0213. Min Act: -0.1700
Data Index: 8282401 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.9275. Min Act: -0.1700
Data Index: 920061 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.8025. Min Act: -0.1700
Data Index: 1665234 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7713. Min Act: -0.1700
Data Index: 4292503 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.8025. Min Act: -0.1700
Data Index: 1759296 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7713. Min Act: -0.1700
Data Index: 3421767 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7713. Min Act: -0.1700
Data Index: 5726550 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7400. Min Act: -0.1700
Data Index: 3051685 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7713. Min Act: -0.1700
Data Index: 7031086 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7088. Min Act: -0.1700
Data Index: 7535240 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7088. Min Act: -0.1700
Data Index: 4895434 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7088. Min Act: -0.1700
Data Index: 5479519 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.6775. Min Act: -0.1700
Data Index: 7998944 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.7088. Min Act: -0.1700
Data Index: 7138084 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7088. Min Range: -6.7088
Max Act: 5.6775. Min Act: -0.1700
Data Index: 2598853 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19