Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.8349. Min Act: -0.1700
Data Index: 8270655 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.7724. Min Act: -0.1700
Data Index: 8470786 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.7724. Min Act: -0.1700
Data Index: 5398165 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.6474. Min Act: -0.1700
Data Index: 4016862 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.5849. Min Act: -0.1700
Data Index: 6757106 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.5849. Min Act: -0.1700
Data Index: 6800935 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.4912. Min Act: -0.1700
Data Index: 5865683 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.5224. Min Act: -0.1700
Data Index: 8772019 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.5224. Min Act: -0.1700
Data Index: 5191425 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.5224. Min Act: -0.1700
Data Index: 3382177 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.4599. Min Act: -0.1700
Data Index: 6266874 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.4287. Min Act: -0.1700
Data Index: 8609042 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.4287. Min Act: -0.1700
Data Index: 7666580 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.3974. Min Act: -0.1700
Data Index: 4260280 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.3974. Min Act: -0.1700
Data Index: 8043688 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.3037. Min Act: -0.1700
Data Index: 593372 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.3349. Min Act: -0.1700
Data Index: 1780810 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.3349. Min Act: -0.1700
Data Index: 7062350 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.3349. Min Act: -0.1700
Data Index: 2367030 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8349. Min Range: -6.8349
Max Act: 6.3349. Min Act: -0.1700
Data Index: 5574029 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19