Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.5789. Min Act: -0.1700
Data Index: 1252503 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.4539. Min Act: -0.1700
Data Index: 602079 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.4539. Min Act: -0.1700
Data Index: 468922 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.3914. Min Act: -0.1700
Data Index: 2484011 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.3289. Min Act: -0.1700
Data Index: 89235 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.3289. Min Act: -0.1700
Data Index: 4728552 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.2664. Min Act: -0.1700
Data Index: 8477164 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.2664. Min Act: -0.1700
Data Index: 4829940 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.2039. Min Act: -0.1700
Data Index: 3390106 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.1414. Min Act: -0.1700
Data Index: 3235064 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0789. Min Act: -0.1700
Data Index: 6612459 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0789. Min Act: -0.1700
Data Index: 7110882 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0789. Min Act: -0.1700
Data Index: 7470879 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0789. Min Act: -0.1700
Data Index: 1037934 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0789. Min Act: -0.1700
Data Index: 4846315 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0789. Min Act: -0.1700
Data Index: 445225 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0164. Min Act: -0.1700
Data Index: 6103912 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0164. Min Act: -0.1700
Data Index: 5372378 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0164. Min Act: -0.1700
Data Index: 5597524 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5789. Min Range: -8.5789
Max Act: 8.0164. Min Act: -0.1700
Data Index: 1453494 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19