Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.2927. Min Act: -0.1700
Data Index: 7684645 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.2302. Min Act: -0.1700
Data Index: 7163177 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.1051. Min Act: -0.1700
Data Index: 4470786 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.1051. Min Act: -0.1700
Data Index: 347426 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0739. Min Act: -0.1700
Data Index: 6153386 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0739. Min Act: -0.1700
Data Index: 2868365 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0426. Min Act: -0.1700
Data Index: 8139988 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0426. Min Act: -0.1700
Data Index: 2081417 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0426. Min Act: -0.1700
Data Index: 7625552 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0114. Min Act: -0.1700
Data Index: 7617499 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0426. Min Act: -0.1700
Data Index: 174684 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0114. Min Act: -0.1700
Data Index: 6846383 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2927. Min Range: -4.2927
Max Act: 4.0114. Min Act: -0.1700
Data Index: 4214744 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2927. Min Range: -4.2927
Max Act: 3.9801. Min Act: -0.1700
Data Index: 2857101 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2927. Min Range: -4.2927
Max Act: 3.9801. Min Act: -0.1700
Data Index: 1213399 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2927. Min Range: -4.2927
Max Act: 3.9176. Min Act: -0.1700
Data Index: 379780 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2927. Min Range: -4.2927
Max Act: 3.9488. Min Act: -0.1700
Data Index: 1132620 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2927. Min Range: -4.2927
Max Act: 3.9488. Min Act: -0.1700
Data Index: 5887943 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2927. Min Range: -4.2927
Max Act: 3.9488. Min Act: -0.1700
Data Index: 3563899 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2927. Min Range: -4.2927
Max Act: 3.9488. Min Act: -0.1700
Data Index: 5430970 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19