Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.1543. Min Act: -0.1700
Data Index: 2956716 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.1386. Min Act: -0.1700
Data Index: 4014413 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.1071. Min Act: -0.1700
Data Index: 5198683 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.0440. Min Act: -0.1700
Data Index: 8058691 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.0755. Min Act: -0.1700
Data Index: 6979907 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.0440. Min Act: -0.1700
Data Index: 4196094 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.0124. Min Act: -0.1700
Data Index: 6711549 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.0124. Min Act: -0.1700
Data Index: 4369044 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9966. Min Act: -0.1700
Data Index: 7971210 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9966. Min Act: -0.1700
Data Index: 8298880 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9966. Min Act: -0.1700
Data Index: 3467699 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9966. Min Act: -0.1700
Data Index: 4438596 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.0124. Min Act: -0.1700
Data Index: 5308333 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1543. Min Range: -3.1543
Max Act: 3.0124. Min Act: -0.1700
Data Index: 479753 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9966. Min Act: -0.1700
Data Index: 1352931 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9808. Min Act: -0.1700
Data Index: 4963440 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9808. Min Act: -0.1700
Data Index: 479752 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9650. Min Act: -0.1700
Data Index: 4781777 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9808. Min Act: -0.1700
Data Index: 7682597 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1543. Min Range: -3.1543
Max Act: 2.9650. Min Act: -0.1700
Data Index: 7682076 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19