Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4169 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2117. Min Range: -5.2117
Max Act: 5.1805. Min Act: -0.1700
Data Index: 7346948 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2117. Min Range: -5.2117
Max Act: 5.2117. Min Act: -0.1700
Data Index: 8106481 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2117. Min Range: -5.2117
Max Act: 5.1492. Min Act: -0.1700
Data Index: 4393381 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2117. Min Range: -5.2117
Max Act: 5.1492. Min Act: -0.1700
Data Index: 1035626 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2117. Min Range: -5.2117
Max Act: 5.0555. Min Act: -0.1700
Data Index: 8690094 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.9930. Min Act: -0.1700
Data Index: 1634263 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.9617. Min Act: -0.1700
Data Index: 2585664 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.9305. Min Act: -0.1700
Data Index: 5393489 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.9305. Min Act: -0.1700
Data Index: 2109778 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.9305. Min Act: -0.1700
Data Index: 8495801 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8992. Min Act: -0.1700
Data Index: 3288479 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8680. Min Act: -0.1700
Data Index: 5818480 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8680. Min Act: -0.1700
Data Index: 7479477 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8367. Min Act: -0.1700
Data Index: 2092782 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8367. Min Act: -0.1700
Data Index: 1400744 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8055. Min Act: -0.1700
Data Index: 777100 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8367. Min Act: -0.1700
Data Index: 5981493 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8367. Min Act: -0.1700
Data Index: 4393388 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8367. Min Act: -0.1700
Data Index: 868257 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2117. Min Range: -5.2117
Max Act: 4.8367. Min Act: -0.1700
Data Index: 6760388 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19