Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.9120. Min Act: -0.1700
Data Index: 2706708 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.7245. Min Act: -0.1700
Data Index: 3832981 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.6933. Min Act: -0.1700
Data Index: 1993885 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.6620. Min Act: -0.1700
Data Index: 1371033 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.5683. Min Act: -0.1700
Data Index: 1899022 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.5370. Min Act: -0.1700
Data Index: 7012661 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.5058. Min Act: -0.1700
Data Index: 5169553 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4745. Min Act: -0.1700
Data Index: 2828423 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4745. Min Act: -0.1700
Data Index: 5209483 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4745. Min Act: -0.1700
Data Index: 607953 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4745. Min Act: -0.1700
Data Index: 8317787 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4745. Min Act: -0.1700
Data Index: 4286312 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4433. Min Act: -0.1700
Data Index: 3226372 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4745. Min Act: -0.1700
Data Index: 69637 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.4433. Min Act: -0.1700
Data Index: 32441 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.3808. Min Act: -0.1700
Data Index: 7773316 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.3495. Min Act: -0.1700
Data Index: 4906309 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.3495. Min Act: -0.1700
Data Index: 4399234 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.3495. Min Act: -0.1700
Data Index: 1668409 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9120. Min Range: -6.9120
Max Act: 6.3495. Min Act: -0.1700
Data Index: 3057376 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19