Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 833 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.3622. Min Act: -0.1700
Data Index: 4886413 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2684. Min Act: -0.1700
Data Index: 976168 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2059. Min Act: -0.1700
Data Index: 4502802 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.2059. Min Act: -0.1700
Data Index: 1693111 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1747. Min Act: -0.1700
Data Index: 6244380 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1434. Min Act: -0.1700
Data Index: 2806162 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1434. Min Act: -0.1700
Data Index: 1556950 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1434. Min Act: -0.1700
Data Index: 5972299 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 8361920 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0809. Min Act: -0.1700
Data Index: 6736282 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 457277 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1434. Min Act: -0.1700
Data Index: 2909864 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1434. Min Act: -0.1700
Data Index: 320101 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0809. Min Act: -0.1700
Data Index: 4548211 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.1122. Min Act: -0.1700
Data Index: 8458871 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0497. Min Act: -0.1700
Data Index: 433187 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0497. Min Act: -0.1700
Data Index: 1210409 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0497. Min Act: -0.1700
Data Index: 5924156 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0184. Min Act: -0.1700
Data Index: 740642 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3622. Min Range: -5.3622
Max Act: 5.0184. Min Act: -0.1700
Data Index: 1136120 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19