Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.2404. Min Act: -0.1700
Data Index: 8434201 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.1466. Min Act: -0.1700
Data Index: 8432048 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.1466. Min Act: -0.1699
Data Index: 1179236 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0841. Min Act: -0.1700
Data Index: 2018851 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0529. Min Act: -0.1700
Data Index: 7573663 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 3291177 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0529. Min Act: -0.1700
Data Index: 1894880 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0529. Min Act: -0.1700
Data Index: 6418226 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 4236461 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 6644484 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 5763712 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0216. Min Act: -0.1696
Data Index: 1820481 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 1910416 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2404. Min Range: -6.2404
Max Act: 6.0216. Min Act: -0.1700
Data Index: 3003314 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2404. Min Range: -6.2404
Max Act: 5.9904. Min Act: -0.1700
Data Index: 7923632 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2404. Min Range: -6.2404
Max Act: 5.9904. Min Act: -0.1700
Data Index: 6753629 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2404. Min Range: -6.2404
Max Act: 5.9904. Min Act: -0.1700
Data Index: 373848 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2404. Min Range: -6.2404
Max Act: 5.9904. Min Act: -0.1700
Data Index: 3466166 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2404. Min Range: -6.2404
Max Act: 5.9904. Min Act: -0.1700
Data Index: 7082353 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2404. Min Range: -6.2404
Max Act: 5.9904. Min Act: -0.1700
Data Index: 6256114 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19