Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 776 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.6727. Min Act: -0.1700
Data Index: 5676303 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.6727. Min Act: -0.1700
Data Index: 1598937 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.6414. Min Act: -0.1700
Data Index: 3709212 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.6102. Min Act: -0.1700
Data Index: 446608 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.5477. Min Act: -0.1700
Data Index: 4216229 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.4852. Min Act: -0.1700
Data Index: 6016511 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.4539. Min Act: -0.1700
Data Index: 5019791 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.4227. Min Act: -0.1700
Data Index: 6662760 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.3914. Min Act: -0.1700
Data Index: 5993424 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.3914. Min Act: -0.1700
Data Index: 630756 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.3602. Min Act: -0.1700
Data Index: 7236736 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.3289. Min Act: -0.1700
Data Index: 7345833 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.3289. Min Act: -0.1700
Data Index: 1336255 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.3289. Min Act: -0.1700
Data Index: 1216039 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.3602. Min Act: -0.1700
Data Index: 8248027 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.2977. Min Act: -0.1700
Data Index: 4630442 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.2664. Min Act: -0.1700
Data Index: 4345967 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.2664. Min Act: -0.1700
Data Index: 2597107 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.2664. Min Act: -0.1700
Data Index: 1269819 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6727. Min Range: -5.6727
Max Act: 5.2352. Min Act: -0.1700
Data Index: 7059074 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19