Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0115. Min Range: -8.0115
Max Act: 8.0115. Min Act: -0.1700
Data Index: 6307158 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.9803. Min Act: -0.1700
Data Index: 4156923 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.9490. Min Act: -0.1700
Data Index: 8492133 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.8553. Min Act: -0.1700
Data Index: 6904428 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.8553. Min Act: -0.1700
Data Index: 6379696 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.7928. Min Act: -0.1700
Data Index: 1127268 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.7615. Min Act: -0.1700
Data Index: 6354463 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.6990. Min Act: -0.1700
Data Index: 2136013 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.6365. Min Act: -0.1700
Data Index: 3330125 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.6365. Min Act: -0.1700
Data Index: 7781447 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.6053. Min Act: -0.1700
Data Index: 5227385 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.5740. Min Act: -0.1700
Data Index: 8064925 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.6053. Min Act: -0.1700
Data Index: 1461956 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.6053. Min Act: -0.1700
Data Index: 810605 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.5740. Min Act: -0.1700
Data Index: 2103898 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.5740. Min Act: -0.1700
Data Index: 4704247 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.5740. Min Act: -0.1700
Data Index: 269804 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.5740. Min Act: -0.1700
Data Index: 1549703 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.5428. Min Act: -0.1700
Data Index: 4149538 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0115. Min Range: -8.0115
Max Act: 7.5428. Min Act: -0.1700
Data Index: 4413309 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19