Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1271 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0901. Min Range: -6.0901
Max Act: 6.0901. Min Act: -0.1700
Data Index: 618234 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0901. Min Range: -6.0901
Max Act: 6.0276. Min Act: -0.1700
Data Index: 7767815 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0901. Min Range: -6.0901
Max Act: 6.0276. Min Act: -0.1700
Data Index: 4827170 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0901. Min Range: -6.0901
Max Act: 6.0276. Min Act: -0.1700
Data Index: 656126 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.9339. Min Act: -0.1700
Data Index: 618235 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.8714. Min Act: -0.1700
Data Index: 4926146 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.9339. Min Act: -0.1700
Data Index: 96695 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.8401. Min Act: -0.1700
Data Index: 704672 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.8089. Min Act: -0.1700
Data Index: 7937632 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.8089. Min Act: -0.1700
Data Index: 7603153 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.8089. Min Act: -0.1700
Data Index: 4767624 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.8089. Min Act: -0.1700
Data Index: 19280 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.7776. Min Act: -0.1700
Data Index: 5725358 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.7464. Min Act: -0.1700
Data Index: 8267161 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.7464. Min Act: -0.1700
Data Index: 8100118 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.7151. Min Act: -0.1700
Data Index: 1821087 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.7464. Min Act: -0.1700
Data Index: 5311739 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.7151. Min Act: -0.1700
Data Index: 2395636 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.6839. Min Act: -0.1700
Data Index: 777524 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0901. Min Range: -6.0901
Max Act: 5.6839. Min Act: -0.1700
Data Index: 2602155 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19