Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4842 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4781. Min Range: -7.4781
Max Act: 7.4781. Min Act: -0.1700
Data Index: 2056429 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4781. Min Range: -7.4781
Max Act: 7.0718. Min Act: -0.1700
Data Index: 3595485 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.9781. Min Act: -0.1700
Data Index: 2025076 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.7281. Min Act: -0.1700
Data Index: 8725324 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.7281. Min Act: -0.1700
Data Index: 2026540 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.6968. Min Act: -0.1700
Data Index: 8667701 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.6031. Min Act: -0.1700
Data Index: 7199854 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.6031. Min Act: -0.1700
Data Index: 312169 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5718. Min Act: -0.1700
Data Index: 207112 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5718. Min Act: -0.1700
Data Index: 3425118 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5406. Min Act: -0.1700
Data Index: 1009864 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5406. Min Act: -0.1700
Data Index: 5719138 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5406. Min Act: -0.1700
Data Index: 7584513 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5406. Min Act: -0.1700
Data Index: 4985888 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5406. Min Act: -0.1700
Data Index: 3190275 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5406. Min Act: -0.1700
Data Index: 5496482 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5406. Min Act: -0.1700
Data Index: 867291 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5093. Min Act: -0.1700
Data Index: 4241104 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.5093. Min Act: -0.1700
Data Index: 5752973 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4781. Min Range: -7.4781
Max Act: 6.4468. Min Act: -0.1700
Data Index: 931657 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19