Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.3501. Min Range: -12.3501
Max Act: 12.3501. Min Act: -0.1700
Data Index: 6894487 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.3501. Min Range: -12.3501
Max Act: 12.2251. Min Act: -0.1700
Data Index: 4242621 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.3501. Min Range: -12.3501
Max Act: 12.1626. Min Act: -0.1700
Data Index: 7191675 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.3501. Min Range: -12.3501
Max Act: 12.1001. Min Act: -0.1700
Data Index: 3424338 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.9751. Min Act: -0.1700
Data Index: 4144194 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.9126. Min Act: -0.1700
Data Index: 8148420 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.9126. Min Act: -0.1700
Data Index: 4491356 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.7876. Min Act: -0.1700
Data Index: 8641089 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.8501. Min Act: -0.1700
Data Index: 7918436 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.7251. Min Act: -0.1700
Data Index: 6840969 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.7251. Min Act: -0.1700
Data Index: 508795 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.6001. Min Act: -0.1700
Data Index: 8701840 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.6001. Min Act: -0.1700
Data Index: 5565308 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.6001. Min Act: -0.1700
Data Index: 840574 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.6001. Min Act: -0.1700
Data Index: 5913276 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.5376. Min Act: -0.1700
Data Index: 360941 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.5376. Min Act: -0.1700
Data Index: 118578 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.5376. Min Act: -0.1700
Data Index: 4651338 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.5376. Min Act: -0.1700
Data Index: 2304476 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.3501. Min Range: -12.3501
Max Act: 11.5376. Min Act: -0.1700
Data Index: 8728548 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19