Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3768 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6694. Min Act: -0.1700
Data Index: 3640041 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6694. Min Act: -0.1700
Data Index: 3949729 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6694. Min Act: -0.1700
Data Index: 8641585 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6068. Min Act: -0.1700
Data Index: 2638751 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6068. Min Act: -0.1700
Data Index: 4145283 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6068. Min Act: -0.1700
Data Index: 6160859 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6068. Min Act: -0.1700
Data Index: 8422042 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6068. Min Act: -0.1700
Data Index: 2182810 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.6068. Min Act: -0.1700
Data Index: 1728993 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 1764597 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 2031860 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 1911727 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 380420 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 42623 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 110749 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 1083353 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 752759 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 712702 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 1843789 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6694. Min Range: -3.6694
Max Act: 3.5755. Min Act: -0.1700
Data Index: 38319 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19