Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0836. Min Range: -6.0836
Max Act: 6.0836. Min Act: -0.1700
Data Index: 7618167 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0836. Min Range: -6.0836
Max Act: 6.0523. Min Act: -0.1700
Data Index: 8342292 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0836. Min Range: -6.0836
Max Act: 6.0211. Min Act: -0.1700
Data Index: 5480890 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.9898. Min Act: -0.1700
Data Index: 4526007 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.9586. Min Act: -0.1700
Data Index: 7589233 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.9586. Min Act: -0.1700
Data Index: 1607860 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.9586. Min Act: -0.1700
Data Index: 6950029 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.9273. Min Act: -0.1700
Data Index: 6182017 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.9273. Min Act: -0.1700
Data Index: 6594637 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8961. Min Act: -0.1700
Data Index: 1835090 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8648. Min Act: -0.1700
Data Index: 1082421 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8648. Min Act: -0.1700
Data Index: 3462818 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8648. Min Act: -0.1700
Data Index: 7550259 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8648. Min Act: -0.1700
Data Index: 9609 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8336. Min Act: -0.1700
Data Index: 5320672 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8023. Min Act: -0.1700
Data Index: 3167973 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8336. Min Act: -0.1700
Data Index: 2249375 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8023. Min Act: -0.1700
Data Index: 7917546 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.8023. Min Act: -0.1700
Data Index: 608628 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0836. Min Range: -6.0836
Max Act: 5.7711. Min Act: -0.1700
Data Index: 3267272 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19