Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1694
Data Index: 8655871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 7877796 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 5670260 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 56931 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 7667121 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 7416487 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 7354031 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 2456960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 8748007 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 8679511 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 2412898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.2783. Min Act: -0.1700
Data Index: 8082333 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.1220. Min Act: -0.1699
Data Index: 6340500 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.0907. Min Act: -0.1700
Data Index: 2215263 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.0907. Min Act: -0.1700
Data Index: 6484344 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.0907. Min Act: -0.1700
Data Index: 4934409 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.0907. Min Act: -0.1700
Data Index: 5109810 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.0907. Min Act: -0.1700
Data Index: 4230664 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.0907. Min Act: -0.1700
Data Index: 3546564 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2783. Min Range: -4.2783
Max Act: 4.0907. Min Act: -0.1700
Data Index: 418884 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19