Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 119 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1870. Min Range: -7.1870
Max Act: 7.1870. Min Act: -0.1700
Data Index: 6238822 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1870. Min Range: -7.1870
Max Act: 7.0307. Min Act: -0.1700
Data Index: 2555832 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1870. Min Range: -7.1870
Max Act: 7.0307. Min Act: -0.1700
Data Index: 1747560 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.9057. Min Act: -0.1700
Data Index: 2350245 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.8432. Min Act: -0.1700
Data Index: 508988 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.8432. Min Act: -0.1700
Data Index: 8650236 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.8120. Min Act: -0.1700
Data Index: 3192452 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.8120. Min Act: -0.1700
Data Index: 4294020 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.7807. Min Act: -0.1700
Data Index: 6127118 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.7182. Min Act: -0.1700
Data Index: 6423751 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.7182. Min Act: -0.1700
Data Index: 938689 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.6870. Min Act: -0.1700
Data Index: 2732212 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.6557. Min Act: -0.1700
Data Index: 3501581 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.6557. Min Act: -0.1700
Data Index: 4558292 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.6557. Min Act: -0.1700
Data Index: 8224839 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.6245. Min Act: -0.1700
Data Index: 534443 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.5620. Min Act: -0.1700
Data Index: 3745627 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.5932. Min Act: -0.1700
Data Index: 5628550 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.5932. Min Act: -0.1700
Data Index: 2119216 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1870. Min Range: -7.1870
Max Act: 6.5932. Min Act: -0.1700
Data Index: 969224 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19