Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0718. Min Range: -7.0718
Max Act: 7.0718. Min Act: -0.1700
Data Index: 3648102 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.8530. Min Act: -0.1700
Data Index: 1984930 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.7905. Min Act: -0.1700
Data Index: 7491043 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.7905. Min Act: -0.1700
Data Index: 3589155 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.7593. Min Act: -0.1700
Data Index: 1063924 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.7280. Min Act: -0.1700
Data Index: 6725083 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.6968. Min Act: -0.1700
Data Index: 3670420 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.6655. Min Act: -0.1700
Data Index: 5062742 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.6343. Min Act: -0.1700
Data Index: 3510362 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.6655. Min Act: -0.1700
Data Index: 2444262 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.6343. Min Act: -0.1700
Data Index: 764763 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.6343. Min Act: -0.1700
Data Index: 3524600 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.6343. Min Act: -0.1700
Data Index: 3743779 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.5718. Min Act: -0.1700
Data Index: 1809728 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.5405. Min Act: -0.1700
Data Index: 469384 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.5405. Min Act: -0.1700
Data Index: 2632534 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.5405. Min Act: -0.1700
Data Index: 2302479 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.5093. Min Act: -0.1700
Data Index: 6716778 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.5093. Min Act: -0.1700
Data Index: 5203889 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0718. Min Range: -7.0718
Max Act: 6.5093. Min Act: -0.1700
Data Index: 3795370 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19