Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4750 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.4653. Min Act: -0.1700
Data Index: 7967379 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.4653. Min Act: -0.1700
Data Index: 5561954 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.4341. Min Act: -0.1700
Data Index: 4913365 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.3716. Min Act: -0.1700
Data Index: 142727 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.3091. Min Act: -0.1700
Data Index: 3025209 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.2778. Min Act: -0.1700
Data Index: 5113370 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.2153. Min Act: -0.1700
Data Index: 8628488 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.2153. Min Act: -0.1700
Data Index: 1290946 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.1528. Min Act: -0.1700
Data Index: 7986674 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.1841. Min Act: -0.1700
Data Index: 6954535 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.1841. Min Act: -0.1700
Data Index: 6571012 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.1528. Min Act: -0.1700
Data Index: 3940899 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.1528. Min Act: -0.1700
Data Index: 1747505 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.1528. Min Act: -0.1700
Data Index: 7613807 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.1216. Min Act: -0.1700
Data Index: 3756355 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.0903. Min Act: -0.1700
Data Index: 6491509 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.0591. Min Act: -0.1700
Data Index: 6795337 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.0591. Min Act: -0.1700
Data Index: 6385085 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.0591. Min Act: -0.1700
Data Index: 8779912 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4653. Min Range: -7.4653
Max Act: 7.0591. Min Act: -0.1700
Data Index: 1916646 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19