Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5104 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1106. Min Range: -7.1106
Max Act: 7.1106. Min Act: -0.1700
Data Index: 8299580 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.5168. Min Act: -0.1700
Data Index: 2080961 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.5168. Min Act: -0.1700
Data Index: 8687820 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.4856. Min Act: -0.1700
Data Index: 8468333 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.3918. Min Act: -0.1700
Data Index: 4990726 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.3918. Min Act: -0.1700
Data Index: 8653184 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.3918. Min Act: -0.1700
Data Index: 1091639 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.2668. Min Act: -0.1700
Data Index: 6400793 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.2668. Min Act: -0.1700
Data Index: 7687138 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.1731. Min Act: -0.1700
Data Index: 7600326 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.1418. Min Act: -0.1700
Data Index: 8660309 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.1731. Min Act: -0.1700
Data Index: 2917075 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.1418. Min Act: -0.1700
Data Index: 7559379 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.1418. Min Act: -0.1700
Data Index: 6339651 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.1106. Min Act: -0.1700
Data Index: 1656131 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.1418. Min Act: -0.1700
Data Index: 3165903 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.0793. Min Act: -0.1700
Data Index: 1091322 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.0793. Min Act: -0.1700
Data Index: 8803573 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.0793. Min Act: -0.1700
Data Index: 7375902 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1106. Min Range: -7.1106
Max Act: 6.0481. Min Act: -0.1700
Data Index: 5560765 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19