Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5237 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2097. Min Range: -5.2097
Max Act: 5.2097. Min Act: -0.1700
Data Index: 4888796 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2097. Min Range: -5.2097
Max Act: 5.1160. Min Act: -0.1700
Data Index: 6192658 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2097. Min Range: -5.2097
Max Act: 5.0535. Min Act: -0.1700
Data Index: 645368 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2097. Min Range: -5.2097
Max Act: 5.0535. Min Act: -0.1700
Data Index: 1895867 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.9910. Min Act: -0.1700
Data Index: 4221638 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.9597. Min Act: -0.1700
Data Index: 3577535 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.9597. Min Act: -0.1700
Data Index: 4349446 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2318710 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.9285. Min Act: -0.1700
Data Index: 4923344 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.9285. Min Act: -0.1700
Data Index: 5977512 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.9285. Min Act: -0.1700
Data Index: 7253155 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8972. Min Act: -0.1700
Data Index: 4923360 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8972. Min Act: -0.1700
Data Index: 4349436 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8660. Min Act: -0.1700
Data Index: 76143 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8660. Min Act: -0.1700
Data Index: 222561 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8660. Min Act: -0.1700
Data Index: 6652247 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8660. Min Act: -0.1700
Data Index: 4692367 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8660. Min Act: -0.1700
Data Index: 462887 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8660. Min Act: -0.1700
Data Index: 5907550 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2097. Min Range: -5.2097
Max Act: 4.8347. Min Act: -0.1700
Data Index: 1328731 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19