Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6196 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.1562. Min Act: -0.1700
Data Index: 5669078 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.1249. Min Act: -0.1700
Data Index: 3601673 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0624. Min Act: -0.1700
Data Index: 6068372 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0624. Min Act: -0.1700
Data Index: 6744622 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0624. Min Act: -0.1700
Data Index: 7164536 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0624. Min Act: -0.1700
Data Index: 7474915 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0624. Min Act: -0.1700
Data Index: 1534102 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 4165521 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 4502179 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 2593121 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 4552232 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 2944161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 5151863 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 7009642 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1562. Min Range: -5.1562
Max Act: 5.0312. Min Act: -0.1700
Data Index: 2264459 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1562. Min Range: -5.1562
Max Act: 4.9999. Min Act: -0.1700
Data Index: 25164 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1562. Min Range: -5.1562
Max Act: 4.9999. Min Act: -0.1700
Data Index: 3420195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1562. Min Range: -5.1562
Max Act: 4.9999. Min Act: -0.1692
Data Index: 7179895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1562. Min Range: -5.1562
Max Act: 4.9999. Min Act: -0.1700
Data Index: 6029758 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1562. Min Range: -5.1562
Max Act: 4.9999. Min Act: -0.1700
Data Index: 5801513 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19